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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12830
    Prev
    Next
    INDEX
    Explanations

    section referencing

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

    This neuron never fires on any tokens (all activations are zero), so it appears to be effectively “dead” and does not detect any pattern.

    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
    が表示
    0.71
    );
    0.70
    })$
    0.69
     otros
    0.68
     индек
    0.67
    ه
    0.67
    StringSet
    0.65
     subscripts
    0.65
    🕹
    0.65
    ))
    0.64
    POSITIVE LOGITS
    ilerin
    0.67
     m
    0.64
    ination
    0.61
    נו
    0.60
    חי
    0.60
     byly
    0.59
     bees
    0.59
    bild
    0.58
     sixty
    0.57
    ภาษา
    0.57
    Activations Density 0.001%

    No Known Activations