© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 211079
    Prev
    Next
    INDEX
    Explanations

    hands make

    np_acts-logits-general · gemini-2.5-flash-lite

    but, contrast, qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     किसके
    0.44
    ники
    0.44
     поведение
    0.44
    ሌ
    0.43
    hesize
    0.42
     दिए
    0.42
    RequestListener
    0.41
    諒
    0.40
    玴
    0.40
    osphate
    0.40
    POSITIVE LOGITS
     მშ
    0.59
     specialising
    0.56
     szko
    0.55
     vattum
    0.55
     cerámica
    0.54
     adap
    0.54
     sakura
    0.53
     adaptés
    0.53
     włas
    0.52
     lecithin
    0.52
    Activations Density 0.001%

    No Known Activations