© 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. 202832
    Prev
    Next
    INDEX
    Explanations

    excellent understanding, primary menu, inordinate paint

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

    opportunities

    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
    Blues
    0.50
    വര
    0.43
    銀座
    0.43
    谌
    0.42
    Flagge
    0.42
    اح
    0.42
    Imagen
    0.42
    枞
    0.41
    Fog
    0.41
     Imagen
    0.41
    POSITIVE LOGITS
    miş
    0.55
    實
    0.50
     CVS
    0.50
     PDT
    0.49
    helpTool
    0.47
     LEAD
    0.47
     PDF
    0.46
     ICT
    0.46
     IPTV
    0.46
     SaaS
    0.46
    Activations Density 0.001%

    No Known Activations