© 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. 49779
    Prev
    Next
    INDEX
    Explanations

    fixed-width integer types and conditions

    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
     Dual
    -0.73
    isOpen
    -0.70
    orty
    -0.68
    rahman
    -0.68
    isson
    -0.68
    eks
    -0.67
    icher
    -0.67
    ceps
    -0.67
     megt
    -0.66
    松山
    -0.66
    POSITIVE LOGITS
    strnc
    0.72
    Protected
    0.71
    "]=
    0.69
     アカ
    0.68
    Quer
    0.65
     Quer
    0.64
     Schoen
    0.64
     protected
    0.64
    Protective
    0.64
    صیل
    0.63
    Activations Density 0.066%

    No Known Activations