© 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. 152465
    Prev
    Next
    INDEX
    Explanations

    defensive scoring

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

    arc lighting, virtual machine, recursively, echo

    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
    LI
    0.52
    V
    0.48
    Fotos
    0.47
    Cot
    0.47
    C
    0.47
    Blob
    0.46
    Visited
    0.46
    Processed
    0.46
    atorium
    0.45
    Valor
    0.44
    POSITIVE LOGITS
     keypad
    0.61
     firmly
    0.60
     imprison
    0.58
     cartel
    0.56
     ტ
    0.55
     snugly
    0.55
     площади
    0.55
     algebraically
    0.54
     ליי
    0.53
     tyrannical
    0.53
    Activations Density 0.000%

    No Known Activations