© 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. 40-GEMMASCOPE-2-RES-262K
    7. 209912
    Prev
    Next
    INDEX
    Explanations

    implementation details and sources

    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_40_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
     शामिल
    0.47
    ריק
    0.43
    <unused3>
    0.43
    Brun
    0.42
     مغربی
    0.42
    栗
    0.42
    ቸው
    0.41
    жев
    0.41
    厡
    0.41
     reicht
    0.40
    POSITIVE LOGITS
     dest
    0.41
     Script
    0.37
     trama
    0.36
     ylabel
    0.36
    script
    0.36
     foment
    0.36
     script
    0.35
     malign
    0.34
     colère
    0.34
     मुख
    0.34
    Activations Density 0.000%

    No Known Activations