© 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. 9911
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years or quantities

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

    The neuron responds strongly to unusually rare or out‐of‐vocabulary tokens (i.e. uncommon words).

    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
    .
    0.82
    ,
    0.75
     Surgeons
    0.74
    )
    0.71
     Attempt
    0.71
    ?
    0.70
     Faz
    0.69
    "
    0.68
     F
    0.67
    '
    0.67
    POSITIVE LOGITS
    getto
    0.84
    酸化
    0.80
    
    0.76
    modations
    0.71
     badań
    0.69
    渡し
    0.68
    ética
    0.67
     méthodes
    0.66
     추진
    0.66
     metodología
    0.66
    Activations Density 0.000%

    No Known Activations