© 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. 48359
    Prev
    Next
    INDEX
    Explanations

    force them to make a decision

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

    sociales, derivatives, technology

    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
    License
    0.46
    气
    0.46
    事
    0.44
    机
    0.44
    拷
    0.44
    BB
    0.44
    FindingsRequest
    0.44
    宽
    0.43
    Status
    0.43
    Session
    0.43
    POSITIVE LOGITS
    ع
    0.51
     towed
    0.48
     tomada
    0.47
    elah
    0.46
     וכ
    0.45
     Terrell
    0.45
    スル
    0.45
    preneur
    0.43
     પ્રેમ
    0.43
     Kein
    0.43
    Activations Density 0.000%

    No Known Activations