© 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. 59384
    Prev
    Next
    INDEX
    Explanations

    chainsaw devil

    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
     programmable
    -0.76
    [+
    -0.75
     prek
    -0.73
    codings
    -0.71
    クエ
    -0.68
    AllowUser
    -0.67
    brü
    -0.67
    sre
    -0.67
    לך
    -0.67
     dep
    -0.67
    POSITIVE LOGITS
     Chains
    1.00
     devil
    0.97
     Devil
    0.96
     chainsaw
    0.91
    Chains
    0.85
    chita
    0.80
     チェ
    0.80
     devils
    0.78
    公安
    0.78
     précédents
    0.77
    Activations Density 0.013%

    No Known Activations