© 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. 97628
    Prev
    Next
    INDEX
    Explanations

    stakeholder engagement

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

    secrets from management

    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
    on
    0.44
    지와
    0.44
     journalistic
    0.43
    R
    0.43
    and
    0.43
    अधिकांश
    0.42
    isin
    0.41
    the
    0.41
    orit
    0.41
    ERCIAL
    0.41
    POSITIVE LOGITS
     继续
    0.48
    JScripts
    0.47
     increí
    0.46
    创作
    0.46
     phòng
    0.46
     sécr
    0.43
     🤗
    0.43
    亲自
    0.43
     схема
    0.42
     প্রমাণ
    0.41
    Activations Density 0.001%

    No Known Activations