© 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. 193727
    Prev
    Next
    INDEX
    Explanations

    reporting issues

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

    parts or descriptions

    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
     Κο
    0.54
     వు
    0.51
     \%$.
    0.49
     bs
    0.47
    的光
    0.46
     mieć
    0.46
     Συν
    0.46
     짧
    0.46
     超
    0.46
     กร
    0.46
    POSITIVE LOGITS
    ド
    0.44
    ontology
    0.43
    ਡੇ
    0.43
    ف
    0.42
    組み立て
    0.42
    ول
    0.42
    prep
    0.41
    坂
    0.41
    trunk
    0.41
    פ
    0.41
    Activations Density 0.001%

    No Known Activations