© 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. 222757
    Prev
    Next
    INDEX
    Explanations

    kits, modules, handler, Chicago

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

    given the context of risk

    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
    ین
    0.49
     protobuf
    0.49
    UN
    0.47
    SE
    0.46
    liquer
    0.46
    𝑽
    0.46
    Ρ
    0.46
     生地
    0.46
    Cache
    0.45
    Geb
    0.45
    POSITIVE LOGITS
     reasonable
    0.44
     sedimentation
    0.42
     palatable
    0.41
     Reasonable
    0.41
     treatment
    0.39
     unambiguously
    0.39
     imminent
    0.39
     plaus
    0.38
     traveling
    0.38
     reasonably
    0.38
    Activations Density 0.001%

    No Known Activations