© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48882
    Prev
    Next
    INDEX
    Explanations

    stopping and braking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     SM
    0.41
    SM
    0.40
    🇺
    0.37
     ремон
    0.37
    ُم
    0.36
     baggy
    0.36
    綗
    0.35
    achet
    0.35
    HttpStatusCode
    0.35
    ্যারি
    0.34
    POSITIVE LOGITS
     Stopping
    0.50
     stopping
    0.49
     brake
    0.48
    Stopping
    0.48
     braking
    0.46
    刹
    0.43
    stopping
    0.42
    軼
    0.42
     останов
    0.41
    停止
    0.41
    Activations Density 0.044%

    No Known Activations