© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    end punctuation after positive state

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

    overview and summary phrases

    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
    7
    0.31
    5
    0.29
     কিংবা
    0.28
    度和
    0.28
    すなわち
    0.27
     or
    0.27
     v
    0.26
     Shah
    0.26
    기와
    0.26
     Delta
    0.26
    POSITIVE LOGITS
    .
    0.44
    。
    0.44
    ។
    0.38
    ।
    0.37
    .`
    0.36
    .“
    0.35
    .​
    0.35
    !?
    0.35
    !
    0.35
    .​​
    0.34
    Activations Density 0.500%

    No Known Activations