© 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. 113565
    Prev
    Next
    INDEX
    Explanations

    tennis / squash rackets

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

    transitional phrases and punctuation

    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
    udie
    0.44
    ére
    0.43
     XIII
    0.43
    ot
    0.43
    ate
    0.41
     jeste
    0.41
    s
    0.41
     XS
    0.41
     работой
    0.41
     CodeableConcept
    0.40
    POSITIVE LOGITS
     iniz
    0.48
    رځ
    0.48
     लगवा
    0.47
    rags
    0.46
    zoa
    0.43
    rag
    0.43
     arka
    0.43
     ра
    0.42
     circ
    0.42
    Chunk
    0.42
    Activations Density 0.001%

    No Known Activations