© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74977
    Prev
    Next
    INDEX
    Explanations

    speaking mission statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Distrito
    0.55
     сожа
    0.51
    )[
    0.51
    !।
    0.49
    ’!
    0.49
     ше
    0.48
    衤
    0.48
    saraba
    0.48
    ༽
    0.48
     cinqui
    0.47
    POSITIVE LOGITS
    ing
    0.39
    dial
    0.39
    BigDecimal
    0.39
    Hasil
    0.38
    Binary
    0.38
    ↵
    0.38
     scalar
    0.38
    Perm
    0.38
    水分
    0.38
    RPG
    0.38
    Activations Density 0.004%

    No Known Activations