© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153385
    Prev
    Next
    INDEX
    Explanations

    individuals, description, sauce

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

    brainstorm, connection, vector

    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
    దా
    0.48
    揪
    0.48
     unavoid
    0.47
     останов
    0.47
    骗
    0.46
    胶
    0.44
    代
    0.44
    奴
    0.44
    띄
    0.43
    렵
    0.43
    POSITIVE LOGITS
     করেছেন
    0.50
    nPort
    0.50
     toujours
    0.49
    opera
    0.49
     書い
    0.48
     printr
    0.47
    lVert
    0.47
    urètre
    0.46
    toRadians
    0.45
    ynth
    0.45
    Activations Density 0.000%

    No Known Activations