© 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. 22-GEMMASCOPE-RES-131K
    7. 129662
    Prev
    Next
    INDEX
    Explanations

    killing enemies and hosts

    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_22/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
    boxShadow
    -0.94
     unsha
    -0.94
    ANTAGE
    -0.93
    zonego
    -0.91
     vitaminas
    -0.90
    锰
    -0.88
    衛隊
    -0.88
    ragos
    -0.88
    jsko
    -0.85
    Bomb
    -0.85
    POSITIVE LOGITS
     targeted
    0.96
     who
    0.94
     marked
    0.94
     captured
    0.89
     engraçado
    0.86
     refleja
    0.85
     asegurado
    0.85
    sneak
    0.84
     whom
    0.84
     сопротив
    0.83
    Activations Density 0.090%

    No Known Activations