© 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. 216795
    Prev
    Next
    INDEX
    Explanations

    thesectionstrashteamcharginggoalsdaysRIGHTS

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

    finding, about, suffer from, process

    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
    да
    0.55
    ди
    0.50
     обуча
    0.46
    aría
    0.46
    ш
    0.45
    マウス
    0.45
    اد
    0.44
    み
    0.44
    従
    0.44
    шт
    0.43
    POSITIVE LOGITS
    atot
    0.49
    Grace
    0.47
     Ashes
    0.47
    。
    0.47
     Grace
    0.46
     Lewis
    0.46
    Lewis
    0.46
    oft
    0.46
     ImageData
    0.46
    eraser
    0.45
    Activations Density 0.000%

    No Known Activations