© 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. 21179
    Prev
    Next
    INDEX
    Explanations

    Yeah, and then

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

    conversational yeah

    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
     に
    0.57
    。</
    0.55
    のです
    0.54
    。[
    0.54
    InputStream
    0.52
    RECTION
    0.50
    ⅰ
    0.50
    मीटर
    0.50
    𝘂
    0.50
    ENCES
    0.49
    POSITIVE LOGITS
    ’
    0.64
     لكن
    0.56
    '
    0.54
    這次
    0.53
    当初
    0.53
    几天
    0.52
     digamos
    0.52
    મ
    0.52
    那个
    0.51
    很难
    0.51
    Activations Density 0.015%

    No Known Activations