© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11466
    Prev
    Next
    INDEX
    Explanations

    modelchecking, model, ':'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    w
    0.55
     &
    0.52
    si
    0.46
    st
    0.46
    r
    0.45
    a
    0.43
    l
    0.43
    t
    0.42
    d
    0.42
    z
    0.42
    POSITIVE LOGITS
     timeCounter
    0.53
    gramModel
    0.52
     resusc
    0.51
    𒇉
    0.49
     sowing
    0.49
     hysterical
    0.49
     ascertaining
    0.49
     paradigma
    0.49
     خفیہ
    0.48
     ہوتا
    0.48
    Activations Density 0.059%

    No Known Activations