© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47809
    Prev
    Next
    INDEX
    Explanations

    unnecessary and formal phrasing

    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_40_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
     Circ
    0.45
    叧
    0.41
    壃
    0.41
    actionBar
    0.41
    🗨
    0.41
     drog
    0.40
     कुत्ते
    0.40
    ногда
    0.40
     जुर्माना
    0.40
     қили
    0.40
    POSITIVE LOGITS
     thr
    0.46
    ovit
    0.41
    proc
    0.39
    យ
    0.37
    QN
    0.37
    Thr
    0.36
    }}^{*}
    0.36
    ak
    0.36
    РУ
    0.36
    IOR
    0.35
    Activations Density 0.001%

    No Known Activations