© 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. 34-GEMMASCOPE-RES-131K
    7. 64678
    Prev
    Next
    INDEX
    Explanations

    Q: followed by text

    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
    uggle
    -0.74
    エール
    -0.71
    嗦
    -0.70
    iev
    -0.68
    𝖚
    -0.67
     апреля
    -0.67
     położ
    -0.66
     sierpnia
    -0.66
    ematica
    -0.66
     creates
    -0.66
    POSITIVE LOGITS
     APPE
    0.97
    traffic
    0.81
     quién
    0.81
    SALUD
    0.80
     fré
    0.78
    PROD
    0.77
     communicative
    0.77
     enthou
    0.75
     aguj
    0.75
    닳
    0.75
    Activations Density 0.009%

    No Known Activations