© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33244
    Prev
    Next
    INDEX
    Explanations

    type classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.12
     Also
    -0.94
     to
    -0.90
     Dont
    -0.90
     In
    -0.90
     into
    -0.85
    jboss
    -0.84
     However
    -0.84
    َ
    -0.83
     Of
    -0.81
    POSITIVE LOGITS
    utiliz
    1.02
    種類の
    1.01
    カテゴリ
    0.99
    čuje
    0.96
     <<"
    0.94
    Lerp
    0.93
    ktan
    0.92
     dekoratif
    0.92
     verschillende
    0.91
    Dienstag
    0.91
    Activations Density 0.009%

    No Known Activations