© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    tow hitches and bumpers

    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
     Astra
    -0.73
    __':
    -0.71
     triad
    -0.71
     объясни
    -0.70
     chiều
    -0.70
    tokenizer
    -0.69
     άν
    -0.69
     Chernobyl
    -0.69
     windscreen
    -0.68
    lor
    -0.67
    POSITIVE LOGITS
     receiver
    1.49
     hitch
    1.48
     bumper
    1.29
     receivers
    1.25
    receiver
    1.23
     tow
    1.14
     Receiver
    1.11
    Receiver
    1.05
     Hitch
    1.03
    bumper
    1.01
    Activations Density 0.014%

    No Known Activations