© 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. 61505
    Prev
    Next
    INDEX
    Explanations

    contact and reservation information

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

    crisis hotlines and phone numbers

    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
    Ს
    0.40
    aranth
    0.39
    ার্চ
    0.38
    ytes
    0.38
     antrop
    0.38
     qualitative
    0.38
    Ა
    0.38
    月份
    0.37
    uxx
    0.37
     exotic
    0.37
    POSITIVE LOGITS
    Email
    0.96
    电话
    0.95
     Email
    0.94
     email
    0.93
     Phone
    0.91
    電話
    0.89
    email
    0.88
     телефон
    0.88
     phone
    0.87
    Phone
    0.86
    Activations Density 0.136%

    No Known Activations