© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127999
    Prev
    Next
    INDEX
    Explanations

    responsibility for

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

    specific languages, tools, or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    >
    0.52
     机
    0.49
     Biol
    0.47
     pH
    0.47
     Pupil
    0.46
     Restore
    0.46
     TBS
    0.46
     Nar
    0.46
     Household
    0.46
     Avon
    0.46
    POSITIVE LOGITS
    wissenschaft
    0.54
    ائيه
    0.52
    غير
    0.51
    ográfico
    0.51
    ladder
    0.47
    厰
    0.47
    cigarette
    0.47
    water
    0.47
    צי
    0.47
    каде
    0.47
    Activations Density 0.000%

    No Known Activations