© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86978
    Prev
    Next
    INDEX
    Explanations

    method names and constructors

    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_34/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
     giving
    -0.87
    って思
    -0.80
     for
    -0.80
     during
    -0.76
     班
    -0.75
     gave
    -0.74
     initiating
    -0.74
     showcasing
    -0.74
     میکن
    -0.73
     each
    -0.72
    POSITIVE LOGITS
    тся
    1.01
    anmoins
    0.87
    rayed
    0.86
    ugais
    0.86
    ")));
    0.84
    TokenNameDOT
    0.84
    ocyan
    0.84
    componentWill
    0.84
    ône
    0.83
    ста
    0.82
    Activations Density 0.010%

    No Known Activations