© 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. 73828
    Prev
    Next
    INDEX
    Explanations

    attributes and service

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

    unit in sentence or rhythm

    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
    ma
    0.52
    鈎
    0.46
    atories
    0.45
    اء
    0.44
     मानदंड
    0.42
    rende
    0.42
    μα
    0.42
    backward
    0.42
    瓴
    0.41
    midt
    0.41
    POSITIVE LOGITS
     attracted
    0.57
     quenched
    0.52
     yielded
    0.50
     zarar
    0.50
     provoked
    0.48
     הרו
    0.47
     ros
    0.46
     wears
    0.46
     Sabtu
    0.46
     연락
    0.45
    Activations Density 0.000%

    No Known Activations