© 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. 31838
    Prev
    Next
    INDEX
    Explanations

    css font properties

    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
    」「
    -0.86
    miede
    -0.82
    日から
    -0.81
    ώ
    -0.81
    hled
    -0.81
    احث
    -0.80
    gier
    -0.79
    зами
    -0.78
     RSSSF
    -0.77
     thence
    -0.77
    POSITIVE LOGITS
    ;
    0.90
     છ
    0.81
    highlights
    0.79
    濮
    0.77
     Favre
    0.77
     BULLETIN
    0.76
     hü
    0.76
     않습니다
    0.76
     LIMITS
    0.75
    orius
    0.75
    Activations Density 0.011%

    No Known Activations