© 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. 65168
    Prev
    Next
    INDEX
    Explanations

    unknown or unspecified details

    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
    ACADEM
    -0.92
     Spirito
    -0.86
    τό
    -0.85
    
    -0.83
     torta
    -0.82
     quarto
    -0.82
    WANTED
    -0.81
    ⁓
    -0.81
     patrio
    -0.81
     strane
    -0.81
    POSITIVE LOGITS
     unknown
    1.17
     unknowns
    1.05
     Exact
    1.02
     unspecified
    1.00
     không
    1.00
    unknown
    0.97
    exact
    0.96
     undetermined
    0.95
    ยัง
    0.95
     chưa
    0.94
    Activations Density 0.080%

    No Known Activations