© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9255
    Prev
    Next
    INDEX
    Explanations

    Root Certificates

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron tends to fire on individual content words that occur as items in a list or series (e.g. “least,” “cost,” “Logo,” “whatever,” “price,” “devices”). In other words, it detects tokens that serve as bullet-style entries in enumerations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciaux
    0.82
    afood
    0.82
     amarelo
    0.81
    ných
    0.79
    Trailer
    0.79
     Север
    0.79
    }})$
    0.79
    的不同
    0.79
    ➼
    0.75
    acés
    0.75
    POSITIVE LOGITS
    as
    0.78
    OOL
    0.73
     reckoning
    0.68
     contracting
    0.66
     collectible
    0.66
     llaman
    0.65
    ↵↵↵
    0.65
     widow
    0.64
     mourning
    0.64
     dear
    0.63
    Activations Density 0.001%

    No Known Activations