© 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. 60069
    Prev
    Next
    INDEX
    Explanations

    reasons and purposes

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

    formality levels and phrasing

    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
    N
    0.51
    Z
    0.51
    J
    0.49
     トー
    0.46
    V
    0.46
     அமெரிக்க
    0.44
     amerik
    0.44
     bạn
    0.43
    B
    0.43
     máte
    0.42
    POSITIVE LOGITS
     reasons
    0.56
     sprawie
    0.51
     Reasons
    0.49
     purposes
    0.49
    理由は
    0.47
     raisons
    0.47
    Reasons
    0.46
     дві
    0.46
     이유는
    0.46
     майже
    0.45
    Activations Density 0.001%

    No Known Activations