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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 422
    Prev
    Next
    INDEX
    Explanations

    categorical labels in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    м
    1.91
    <bos>
    1.76
    iation
    1.61
    iore
    1.56
    शिव
    1.53
    usd
    1.53
    en
    1.51
    elves
    1.39
    ziale
    1.38
    iya
    1.35
    POSITIVE LOGITS
    ?!?
    2.32
    ?!?!
    2.07
    !!!!!!
    1.78
    !!!!!!!
    1.77
    魎
    1.73
    !!!!!!!!
    1.60
    DOCTYPE
    1.55
     kupu
    1.51
     प्राण
    1.46
     साफ
    1.44
    Activations Density 0.365%

    No Known Activations