© 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. 24271
    Prev
    Next
    INDEX
    Explanations

    property copyright

    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
     aspirated
    0.51
    हिंदी
    0.46
    aspir
    0.45
     naturelles
    0.44
    Current
    0.43
    ಙ
    0.42
     naturales
    0.42
    ewną
    0.42
    ธรรมชาติ
    0.41
    自然的
    0.41
    POSITIVE LOGITS
     bro
    0.41
    寫
    0.36
    жит
    0.35
    lef
    0.35
     dor
    0.34
    ELF
    0.34
    批
    0.34
    حي
    0.34
     Eltern
    0.34
    Read
    0.33
    Activations Density 0.001%

    No Known Activations