© 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. 41-GEMMASCOPE-2-RES-262K
    7. 64009
    Prev
    Next
    INDEX
    Explanations

    counting and hashing

    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_all/layer_41_width_262k_l0_big
    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
     그리고
    0.42
     ܘ
    0.41
     הרו
    0.41
     వచ్చిన
    0.40
     gerade
    0.40
     прад
    0.39
    ਪਣ
    0.38
     Royals
    0.38
    ㄝ
    0.38
     ਅਤੇ
    0.37
    POSITIVE LOGITS
     Pathology
    0.40
    Sne
    0.40
    /*
    0.40
    Geography
    0.39
    Open
    0.39
    Tile
    0.38
    Fract
    0.38
    Paste
    0.38
    वीं
    0.37
    resist
    0.37
    Activations Density 0.066%

    No Known Activations