© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129502
    Prev
    Next
    INDEX
    Explanations

    / followed by names

    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
     something
    -0.88
    uncio
    -0.88
    sistent
    -0.84
     нази
    -0.82
     correspon
    -0.82
    cising
    -0.81
     rhein
    -0.79
    Good
    -0.79
     this
    -0.77
    票房
    -0.77
    POSITIVE LOGITS
     primeros
    1.11
    ῶ
    1.01
     čier
    0.97
    емъ
    0.97
     Vernunft
    0.96
     adelant
    0.94
     Usaha
    0.93
     nový
    0.93
    getIntent
    0.93
    kje
    0.92
    Activations Density 0.046%

    No Known Activations