© 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. 178705
    Prev
    Next
    INDEX
    Explanations

    specific items and actions

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

    word/token structures

    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
    D
    0.63
    Canvas
    0.56
    Aster
    0.56
    Analysis
    0.55
    0
    0.54
    q
    0.53
    the
    0.53
    Response
    0.51
    development
    0.51
    x
    0.51
    POSITIVE LOGITS
     букмекердик
    0.51
     NSTX
    0.51
     TRPV
    0.49
     klinik
    0.48
     RNG
    0.47
     TMD
    0.47
    临床
    0.47
     PBMCs
    0.47
    বিষ্ট
    0.46
     hMut
    0.46
    Activations Density 0.000%

    No Known Activations