© 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. 34653
    Prev
    Next
    INDEX
    Explanations

    special offers

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

    depends on context

    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
    ustainable
    0.28
    ’
    0.27
    ceed
    0.26
     về
    0.25
    <0xE1>
    0.25
     tagline
    0.25
     depicts
    0.25
    áž
    0.25
     reimag
    0.25
    ية
    0.25
    POSITIVE LOGITS
    었고
    0.25
     langsam
    0.23
     весь
    0.22
     совсем
    0.22
    으니
    0.21
    ฟา
    0.21
     mutta
    0.21
    溽
    0.21
     но
    0.21
     circonstances
    0.21
    Activations Density 0.003%

    No Known Activations