© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 498
    Prev
    Next
    INDEX
    Explanations

    army and military events

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining concepts or rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宾
    0.55
    DeviceCompliance
    0.48
    賓
    0.47
    朝鲜
    0.47
    enza
    0.46
    EAST
    0.45
    Benzyloxy
    0.45
    jaman
    0.44
    东
    0.44
    East
    0.44
    POSITIVE LOGITS
     entrants
    0.53
     ordinary
    0.52
     Ordinary
    0.52
     heats
    0.51
     patents
    0.50
     grau
    0.50
     unaffected
    0.50
     speculators
    0.50
     Famer
    0.49
     sweats
    0.49
    Activations Density 0.000%

    No Known Activations