© 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. 48457
    Prev
    Next
    INDEX
    Explanations

    put forward proposed theories

    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
     Achie
    -0.86
     fragen
    -0.82
    vh
    -0.81
    tivos
    -0.77
    vertrag
    -0.74
    ULUS
    -0.73
     zeigt
    -0.72
    殃
    -0.71
     SPECIFICATION
    -0.71
    JNIEnv
    -0.71
    POSITIVE LOGITS
     offered
    2.56
     advanced
    2.41
     presented
    2.38
    提出
    1.98
     advance
    1.93
     put
    1.92
     offer
    1.92
     ارائه
    1.89
     proposed
    1.86
     Offered
    1.85
    Activations Density 0.085%

    No Known Activations