© 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. 206700
    Prev
    Next
    INDEX
    Explanations

    worlds, their, lives, capture

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

    even if

    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
     Tokugawa
    0.59
     for
    0.53
    ية
    0.52
    ﺩ
    0.52
     forbidden
    0.50
     Unión
    0.50
     saldır
    0.49
     atac
    0.48
    య
    0.48
    entarios
    0.46
    POSITIVE LOGITS
     droughts
    0.45
     ಕೇ
    0.43
    らし
    0.40
    ଟି
    0.40
    一顆
    0.40
    会の
    0.39
    驟
    0.39
    BUT
    0.39
    ді
    0.39
    باً
    0.39
    Activations Density 0.000%

    No Known Activations