© 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. 32293
    Prev
    Next
    INDEX
    Explanations

    voltage, resistance, and forward bias

    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
    gnac
    -0.81
     security
    -0.75
     Security
    -0.73
    bellar
    -0.73
     moment
    -0.72
     orientation
    -0.70
     Languages
    -0.70
     winding
    -0.69
    Security
    -0.69
     boost
    -0.69
    POSITIVE LOGITS
     Cheddar
    0.80
     Cheung
    0.80
    itern
    0.73
     تضيفلها
    0.71
     delante
    0.70
    Recom
    0.70
     Sponsored
    0.70
    囗
    0.69
     RECOMM
    0.68
     VIDEOT
    0.68
    Activations Density 0.022%

    No Known Activations