© 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. 125912
    Prev
    Next
    INDEX
    Explanations

    Distress, locker, softcore, x86

    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
     येतो
    0.48
    𝟏
    0.48
    Descripción
    0.48
     فيه
    0.47
    തിനുള്ള
    0.43
     contradicts
    0.43
    兘
    0.43
    玹
    0.43
     String
    0.42
     Jews
    0.42
    POSITIVE LOGITS
    yai
    0.47
    .
    0.46
    ми
    0.46
    at
    0.46
    웍
    0.45
    ма
    0.44
    ypass
    0.43
    م
    0.43
    mıştı
    0.42
     incap
    0.42
    Activations Density 0.006%

    No Known Activations