© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22976
    Prev
    Next
    INDEX
    Explanations

    8k, Grain, INC

    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
    ดิ
    0.37
    ⤒
    0.36
    いただ
    0.35
     számára
    0.34
     inci
    0.34
    しも
    0.34
    Interest
    0.34
     असता
    0.33
    schnitt
    0.33
     Interesse
    0.32
    POSITIVE LOGITS
    )}{\
    0.35
    embalikan
    0.35
    lol
    0.35
    ilizce
    0.35
    রির
    0.34
     afectado
    0.34
    IG
    0.33
     ప్రే
    0.33
     cationic
    0.33
    দ্বিত
    0.33
    Activations Density 0.038%

    No Known Activations