© 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. 66029
    Prev
    Next
    INDEX
    Explanations

    night

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

    clear view, felt sick, failed idea

    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
    あなた
    0.49
    respuesta
    0.49
    こちらの
    0.47
    ಮ್
    0.46
    ב
    0.46
    Е
    0.45
    NOTA
    0.45
    લ
    0.45
    אם
    0.44
    neighbour
    0.44
    POSITIVE LOGITS
     nightly
    0.46
     Noct
    0.45
    允许
    0.44
     ночью
    0.44
     pozwoli
    0.42
     তখন
    0.42
     nahezu
    0.42
     ở
    0.41
     Nights
    0.41
     夜
    0.41
    Activations Density 0.002%

    No Known Activations