© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 161745
    Prev
    Next
    INDEX
    Explanations

    job titles/professions

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

    Avoid debate

    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
     spreading
    0.48
     biopsies
    0.45
     couches
    0.44
    soul
    0.44
     sofas
    0.44
    稈
    0.44
    acks
    0.44
    лые
    0.44
    ссажи
    0.44
    🌖
    0.44
    POSITIVE LOGITS
     maîtrise
    0.55
    FRAMERATE
    0.49
     Delta
    0.48
     kilometre
    0.47
     controle
    0.45
    PSP
    0.45
     cdr
    0.44
    ”
    0.44
     PDP
    0.44
    PDP
    0.44
    Activations Density 0.001%

    No Known Activations