© 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. 173002
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    packaging, Fibers, Pitching, tracing

    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
    setDescription
    0.44
    化
    0.44
    }--\
    0.43
     چې
    0.43
     numberOf
    0.43
    泣
    0.43
    compose
    0.42
     flush
    0.42
    flush
    0.41
     recount
    0.41
    POSITIVE LOGITS
    śmy
    0.52
     Dafür
    0.51
    ֑
    0.50
    jala
    0.49
    ן
    0.49
     महात्मा
    0.49
    אים
    0.49
    drig
    0.48
    olai
    0.47
    fangs
    0.47
    Activations Density 0.000%

    No Known Activations