© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93110
    Prev
    Next
    INDEX
    Explanations

    what we

    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
    感じが
    -1.07
    ところは
    -1.05
     afectadas
    -1.04
    potentially
    -0.99
    ੱਕ
    -0.99
    cerer
    -0.98
     võib
    -0.98
    おもしろ
    -0.98
     disfru
    -0.97
     навіть
    -0.97
    POSITIVE LOGITS
     университета
    0.89
    Irish
    0.86
    --------------
    0.82
    👗
    0.82
    🌻
    0.82
     nigra
    0.81
    -----------
    0.80
    Court
    0.78
    🌿
    0.76
    ~~~~~
    0.75
    Activations Density 0.000%

    No Known Activations