© 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. 34-GEMMASCOPE-RES-131K
    7. 31162
    Prev
    Next
    INDEX
    Explanations

    descriptive or informative output

    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
     molle
    -0.84
    addKeyListener
    -0.83
     مدرن
    -0.83
    주의
    -0.82
    えたら
    -0.81
    vább
    -0.79
    ೌ
    -0.79
    CharArray
    -0.78
     État
    -0.78
     matériel
    -0.77
    POSITIVE LOGITS
     meaningful
    3.17
     descriptive
    2.16
     sensible
    1.97
     useful
    1.97
     helpful
    1.88
     informative
    1.88
    Descriptive
    1.85
     meaningfully
    1.80
    meaning
    1.65
     understandable
    1.61
    Activations Density 0.164%

    No Known Activations