© 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. 169859
    Prev
    Next
    INDEX
    Explanations

    verse numbers like 5:15

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

    optimize, best solutions

    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
    ।
    0.49
    ματος
    0.48
    neurons
    0.46
     Trabaj
    0.46
     रचना
    0.46
     correto
    0.46
    ﻭ
    0.46
     ।
    0.45
    યો
    0.45
    ijos
    0.45
    POSITIVE LOGITS
     manoeuvre
    0.48
     manoeuv
    0.45
     המו
    0.45
     konzent
    0.42
    Estimate
    0.41
     maneu
    0.41
    集中
    0.39
    ′-
    0.38
    MsgCallBack
    0.38
     xlink
    0.38
    Activations Density 0.001%

    No Known Activations