© 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. 233024
    Prev
    Next
    INDEX
    Explanations

    entitled to, who specializes, user cache

    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
    쏨
    0.46
    㻴
    0.45
     testamentary
    0.45
    쿰
    0.45
    헨
    0.45
    申
    0.45
    期限
    0.44
     nanof
    0.44
    翰
    0.43
     Placement
    0.43
    POSITIVE LOGITS
     qu
    0.46
     ventana
    0.46
     violated
    0.45
     forbade
    0.45
    ،
    0.45
     প্রতিরোধ
    0.44
    )\
    0.44
     pois
    0.44
    ];
    0.44
     prea
    0.43
    Activations Density 0.001%

    No Known Activations