© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63686
    Prev
    Next
    INDEX
    Explanations

    store, deal, app, MOV, SJ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     театр
    0.46
    ui
    0.46
    szág
    0.46
    sp
    0.44
     Illness
    0.44
     Of
    0.44
     headed
    0.43
    g
    0.43
     prud
    0.42
     Six
    0.42
    POSITIVE LOGITS
     ನಾನು
    0.55
    einander
    0.50
    🌠
    0.50
     grandiose
    0.47
    💫
    0.46
     होप
    0.46
     ረ
    0.45
     excitations
    0.45
     дизайна
    0.44
    🥹
    0.44
    Activations Density 0.013%

    No Known Activations