© 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. 244188
    Prev
    Next
    INDEX
    Explanations

    add the

    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
    Bodies
    0.47
    宗
    0.45
    clonal
    0.44
    bodies
    0.44
     නොව
    0.43
    決
    0.43
     വിഷയ
    0.42
     最高
    0.41
     কর্ম
    0.41
    vers
    0.40
    POSITIVE LOGITS
    INGO
    0.52
     langchain
    0.49
     finland
    0.48
     lighten
    0.47
     inch
    0.47
     eines
    0.47
    AI
    0.46
     т
    0.46
    IDUAL
    0.46
     falcon
    0.45
    Activations Density 0.000%

    No Known Activations