© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    choice, nature, or state

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

    end of explanatory sentence

    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
     for
    0.33
    లో
    0.33
     foe
    0.32
    йн
    0.32
    などで
    0.31
    х
    0.31
    で
    0.31
     для
    0.31
     уйнагыз
    0.31
    ках
    0.30
    POSITIVE LOGITS
    。
    0.39
    。『
    0.38
     ใคร
    0.36
    ۔
    0.34
    这才
    0.32
    。《
    0.31
    。「
    0.31
    ។
    0.31
     आखिरकार
    0.31
     Combien
    0.31
    Activations Density 0.402%

    No Known Activations