© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28889
    Prev
    Next
    INDEX
    Explanations

    be able

    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_40_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
    watcher
    0.42
    сподар
    0.42
    ŵ
    0.41
    蝌
    0.41
    licher
    0.41
    thisTrack
    0.40
     говорили
    0.40
     देत
    0.40
    ঋ
    0.39
    ǯ
    0.39
    POSITIVE LOGITS
     able
    0.88
     replaced
    0.69
     transferred
    0.68
     implemented
    0.65
     converted
    0.62
     done
    0.61
     included
    0.61
     interpreted
    0.60
     accessed
    0.60
     taxed
    0.60
    Activations Density 0.007%

    No Known Activations