© 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. 105071
    Prev
    Next
    INDEX
    Explanations

    joining an activity or group

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

    thermodynamics or digestive systems

    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
    دام
    0.53
    ometraje
    0.52
    屾
    0.47
    د
    0.46
    ibilité
    0.46
    isValue
    0.45
    лле
    0.44
    ించింది
    0.44
     participaron
    0.44
     EdgeInsets
    0.44
    POSITIVE LOGITS
    quality
    0.48
     inputted
    0.47
    <s>
    0.46
    sphere
    0.46
     예술
    0.45
     sensors
    0.45
    cinema
    0.45
    courses
    0.44
    Theater
    0.44
    zb
    0.43
    Activations Density 0.002%

    No Known Activations