© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135190
    Prev
    Next
    INDEX
    Explanations

    cleverly explores information

    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
     bale
    0.39
    to
    0.38
     ധ
    0.38
     Kg
    0.36
    สำเร็จ
    0.36
     Hills
    0.36
    Kg
    0.36
    ты
    0.35
    fois
    0.35
     ре
    0.35
    POSITIVE LOGITS
     مرتب
    0.45
     guardians
    0.43
    ’!
    0.42
    덤
    0.41
    olytic
    0.40
     एप्ली
    0.40
    পের
    0.39
     spliced
    0.39
    '}}>
    0.38
     Cooley
    0.38
    Activations Density 0.001%

    No Known Activations