© 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. 143868
    Prev
    Next
    INDEX
    Explanations

    diverse languages and specific dates

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

    Real Power, Superior Approval, git branch

    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
    ke
    0.59
    and
    0.54
    io
    0.54
    Detail
    0.53
    dR
    0.53
    ius
    0.51
    &=
    0.51
    ic
    0.50
    Count
    0.50
    ffe
    0.49
    POSITIVE LOGITS
     бушлай
    0.50
     Oaxaca
    0.50
     midday
    0.50
    прода
    0.49
     oxidant
    0.49
     março
    0.48
     lunchtime
    0.47
     Temmuz
    0.47
     julho
    0.47
     noviembre
    0.46
    Activations Density 0.002%

    No Known Activations