© 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. 58403
    Prev
    Next
    INDEX
    Explanations

    concrete

    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
     lem
    0.41
    釜
    0.41
     záb
    0.40
    ἥ
    0.40
    กำ
    0.39
     glands
    0.38
     espíritu
    0.38
     fixture
    0.38
    灞
    0.38
     விய
    0.37
    POSITIVE LOGITS
     concrete
    0.92
    concrete
    0.80
    Concrete
    0.80
     concreto
    0.79
     Concrete
    0.78
     concreta
    0.75
     concret
    0.71
     бетон
    0.70
    concret
    0.70
    混凝土
    0.68
    Activations Density 0.002%

    No Known Activations