© 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. 25194
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    * issue follows

    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
    설
    0.39
    輒
    0.39
     booths
    0.38
     ghép
    0.37
     ל
    0.37
    GTA
    0.36
     丨
    0.36
    घा
    0.36
    
    0.36
     amplia
    0.35
    POSITIVE LOGITS
    こちらも
    0.63
     again
    0.55
    again
    0.52
     Again
    0.51
    这也是
    0.51
    これも
    0.49
     역시
    0.46
    Again
    0.45
    역시
    0.44
     আবারো
    0.44
    Activations Density 0.075%

    No Known Activations