© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41525
    Prev
    Next
    INDEX
    Explanations

    specific nouns following common words

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

    size or scale

    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
    و
    0.58
    Curt
    0.46
    로는
    0.46
     کي
    0.45
    ،
    0.45
    庐
    0.44
     ۽
    0.44
    ла
    0.43
     شراب
    0.43
     أش
    0.42
    POSITIVE LOGITS
     tonne
    0.49
     reiter
    0.49
     enticing
    0.48
    ymmetric
    0.48
     replicas
    0.46
     strtoupper
    0.46
     reiterated
    0.46
     conglomerates
    0.45
     endorsing
    0.45
    etric
    0.45
    Activations Density 0.000%

    No Known Activations