© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11914
    Prev
    Next
    INDEX
    Explanations

    interact, demand, initially, Assumption, complex, into

    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_31_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
    त
    0.52
    ಡುವ
    0.48
    un
    0.46
    お
    0.46
    Us
    0.46
    व
    0.45
    Todas
    0.44
    Municipio
    0.43
    te
    0.43
    테
    0.42
    POSITIVE LOGITS
    ».
    0.48
     секре
    0.44
    QueryResult
    0.43
     নাট
    0.42
    जरीवाल
    0.42
     Conversely
    0.42
     сами
    0.40
     রুশ
    0.40
    aların
    0.39
    คืน
    0.39
    Activations Density 0.003%

    No Known Activations