© 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. 96667
    Prev
    Next
    INDEX
    Explanations

    decline, empty, when, is, until, was

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

    nonchalant, confident, sentences

    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
    mo
    0.46
    ﺭ
    0.44
    mal
    0.43
    pol
    0.43
     arts
    0.43
    措
    0.40
    kar
    0.40
     firstName
    0.39
     birbir
    0.39
     thermally
    0.38
    POSITIVE LOGITS
     忄
    0.56
    utérus
    0.55
    aigu
    0.54
     hạt
    0.53
    пии
    0.53
    effectuer
    0.53
    фель
    0.53
    Экс
    0.53
    PKG
    0.52
     ◇
    0.51
    Activations Density 0.002%

    No Known Activations