© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    month name and punctuation

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

    market analysis and competition

    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
    ற்
    0.46
    ペ
    0.43
     पेंट
    0.42
    flowLayoutPanel
    0.42
    🌬
    0.40
    ников
    0.40
    Shakespeare
    0.40
    阔
    0.40
    텐
    0.40
    ुत
    0.39
    POSITIVE LOGITS
    aisse
    0.43
     ench
    0.41
    esar
    0.39
    .</
    0.38
    ipher
    0.38
    atura
    0.38
     dagli
    0.37
     statist
    0.37
    inkler
    0.37
    elta
    0.37
    Activations Density 0.000%

    No Known Activations