© 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. 58646
    Prev
    Next
    INDEX
    Explanations

    dates and sequences

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

    updated independently

    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
    Ꭳ
    0.55
    والفقار
    0.49
     decimos
    0.48
     percorso
    0.47
    ໃຊ
    0.47
    캥
    0.46
     diciamo
    0.46
    IRI
    0.46
    एसआय
    0.46
     Không
    0.46
    POSITIVE LOGITS
     chron
    0.54
    n
    0.50
     Chron
    0.49
     против
    0.48
     freestanding
    0.44
     chronological
    0.44
    ism
    0.44
    athon
    0.43
    s
    0.42
     _{\
    0.41
    Activations Density 0.000%

    No Known Activations