© 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. 64119
    Prev
    Next
    INDEX
    Explanations

    defensive pistol calibers and carry

    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
     rifle
    -0.86
    ột
    -0.82
    NBT
    -0.79
     tono
    -0.79
    ServiceClient
    -0.76
     Nere
    -0.76
    ၾ
    -0.76
     rifles
    -0.75
     Warden
    -0.74
    醪
    -0.73
    POSITIVE LOGITS
     holster
    1.32
     hol
    0.95
     Hol
    0.78
     LEM
    0.72
    Plugins
    0.72
     defense
    0.71
    QUOTE
    0.69
     писто
    0.68
     Defensive
    0.68
     použ
    0.68
    Activations Density 0.021%

    No Known Activations