© 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. 45394
    Prev
    Next
    INDEX
    Explanations

    year, end, you

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

    explanation of a situation

    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
    AH
    0.43
     Respect
    0.43
     SH
    0.40
    SH
    0.40
     Peace
    0.40
     OH
    0.40
    ˈ
    0.39
    巴士
    0.39
     Stability
    0.38
    વવા
    0.38
    POSITIVE LOGITS
     podríamos
    0.60
     podamos
    0.54
     possam
    0.54
     thok
    0.52
     asing
    0.51
     podrían
    0.50
    aol
    0.50
     aportar
    0.48
     puissent
    0.48
    ូត
    0.48
    Activations Density 0.000%

    No Known Activations