© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51157
    Prev
    Next
    INDEX
    Explanations

    following descriptions or lists

    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
    ת
    0.58
    ﺔ
    0.58
    לי
    0.56
    ﻬ
    0.56
     ל
    0.53
    ﻴ
    0.53
     מ
    0.52
    רה
    0.52
     являются
    0.52
    ﻨ
    0.52
    POSITIVE LOGITS
     fades
    0.48
    Xs
    0.43
    ."))
    0.42
    ?
    0.42
     decays
    0.42
     shaders
    0.41
    unload
    0.41
     ascend
    0.39
     indistinct
    0.39
     sluggish
    0.39
    Activations Density 0.000%

    No Known Activations