© 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. 35485
    Prev
    Next
    INDEX
    Explanations

    light bulb

    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
     عليك
    0.40
     khoản
    0.40
    égalité
    0.39
    ષ્ઠ
    0.39
    ඃ
    0.39
    экс
    0.38
    会对
    0.38
    affles
    0.38
    ipolar
    0.38
     レッド
    0.38
    POSITIVE LOGITS
    ది
    0.39
     Wave
    0.39
     mitigating
    0.39
     Food
    0.39
    <0xBB>
    0.38
     search
    0.38
     brim
    0.37
    sses
    0.37
     Addresses
    0.37
    事故
    0.37
    Activations Density 0.000%

    No Known Activations