© 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. 165548
    Prev
    Next
    INDEX
    Explanations

    Cruz, employers, cost, solely

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

    Secure Hiring, holds everything

    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
    謡
    0.50
     photographing
    0.46
    </code>
    0.46
    按照
    0.46
     स्ट्रीट
    0.45
    ஜின
    0.45
    engono
    0.45
    PWM
    0.45
    piano
    0.44
     resolving
    0.44
    POSITIVE LOGITS
     Sache
    0.52
     Harp
    0.45
     Org
    0.45
     forts
    0.44
    aré
    0.44
     Idee
    0.44
    <>();
    0.42
    astres
    0.42
    erté
    0.41
     ว่า
    0.41
    Activations Density 0.000%

    No Known Activations