© 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. 232312
    Prev
    Next
    INDEX
    Explanations

    official documents

    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
    ρα
    0.47
    賃
    0.47
    箇所
    0.46
    ếc
    0.46
    हायला
    0.46
    損
    0.46
    橄
    0.46
    POSTFIELDS
    0.44
    И
    0.44
    ...\...\
    0.44
    POSITIVE LOGITS
    lord
    0.56
     Petition
    0.55
     wers
    0.50
     yoki
    0.49
    ods
    0.48
     Partition
    0.47
     manda
    0.47
    აციის
    0.46
     Chord
    0.46
    petition
    0.46
    Activations Density 0.001%

    No Known Activations