© 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. 64074
    Prev
    Next
    INDEX
    Explanations

    dividend, Fibonacci, five, writing, surface, personal

    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
     pater
    0.41
     Ambedkar
    0.38
     omission
    0.38
     நூல்
    0.37
    <unused11>
    0.37
     mon
    0.36
    日至
    0.36
     allowNull
    0.36
    ሣ
    0.36
     Lew
    0.36
    POSITIVE LOGITS
     wysoko
    0.42
    UTILS
    0.40
    DAV
    0.39
    测量
    0.38
    يش
    0.37
    Measurements
    0.37
    يمان
    0.37
    Looks
    0.36
    Wales
    0.36
    Bio
    0.36
    Activations Density 0.565%

    No Known Activations