© 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. 138813
    Prev
    Next
    INDEX
    Explanations

    heroic, shoulder, Sky, Hope, happy

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

    AI development and scientific concepts

    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
     методи
    0.52
     microseconds
    0.47
     BCA
    0.46
     тариф
    0.46
     говорили
    0.46
    >≥</
    0.46
     centrifugation
    0.46
     projection
    0.45
     peso
    0.45
     strangled
    0.45
    POSITIVE LOGITS
     twor
    0.54
    این
    0.49
     It
    0.49
    C
    0.47
    Ihr
    0.46
    Stop
    0.46
    铎
    0.46
     Tiny
    0.45
    Crew
    0.45
    繡
    0.45
    Activations Density 0.000%

    No Known Activations