© 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. 38280
    Prev
    Next
    INDEX
    Explanations

    list structure, code delimiters

    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
    ;
    -0.96
     allergy
    -0.88
    uttg
    -0.88
    :
    -0.85
     under
    -0.84
     Example
    -0.81
     Use
    -0.80
    oughton
    -0.80
     If
    -0.80
     This
    -0.80
    POSITIVE LOGITS
    Polizei
    0.93
     nové
    0.92
    ឋ
    0.89
     LINES
    0.88
    --)
    0.88
    Puissance
    0.87
     ciri
    0.87
     grotte
    0.86
    izate
    0.85
     NATURE
    0.85
    Activations Density 0.018%

    No Known Activations