© 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. 187839
    Prev
    Next
    INDEX
    Explanations

    insurance and specific inquiries

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

    track targets, negotiate salary, manipulate others

    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
    of
    0.48
    TT
    0.48
    BT
    0.47
    to
    0.46
    $\
    0.46
    FC
    0.46
    ¬
    0.46
     sendiri
    0.45
    ิ
    0.45
    ^{\
    0.44
    POSITIVE LOGITS
     belangrijke
    0.49
     hyperlinks
    0.47
     الطاقة
    0.46
     Zoho
    0.46
    ركات
    0.45
     endereço
    0.45
     linkages
    0.43
    દર
    0.43
    닝
    0.43
     DHCP
    0.43
    Activations Density 0.001%

    No Known Activations