© 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. 6196
    Prev
    Next
    INDEX
    Explanations

    state completion or boundary

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

    ending punctuation or alternatives

    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
     চ
    0.38
     সময়
    0.37
     চল্লিশ
    0.36
     আমার
    0.36
    ที่จะ
    0.35
    ដើម្បី
    0.35
     όσο
    0.34
     এখানকার
    0.34
    様専用
    0.34
     ಇಲ್ಲಿ
    0.34
    POSITIVE LOGITS
    ®.
    0.51
    。
    0.50
    ។
    0.45
    🤯
    0.45
    。『
    0.43
    。「
    0.42
    otherwise
    0.42
    ;.
    0.41
    ።
    0.41
    ;
    0.40
    Activations Density 0.503%

    No Known Activations