© 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. 240157
    Prev
    Next
    INDEX
    Explanations

    different types, penguin documentary, coached me

    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
    fillText
    0.52
    衷
    0.47
    seat
    0.46
    powr
    0.46
    textContent
    0.45
     Seat
    0.45
    Mud
    0.44
    innerText
    0.44
    liminf
    0.44
    game
    0.43
    POSITIVE LOGITS
     разом
    0.54
     生地
    0.52
     ૩
    0.51
     honti
    0.50
     ㅣ
    0.50
     invigor
    0.50
    ン
    0.50
     primeiros
    0.49
     reinvigor
    0.49
    ゴム
    0.49
    Activations Density 0.001%

    No Known Activations