© 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. 50494
    Prev
    Next
    INDEX
    Explanations

    opening / stage

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

    technical actions and states

    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
     எப்ப
    0.50
    孭
    0.48
    那么多
    0.47
    屐
    0.46
     horr
    0.46
     كلها
    0.45
     tellement
    0.45
     একটা
    0.45
    maßen
    0.45
    赔
    0.44
    POSITIVE LOGITS
     initialization
    0.50
     preprocessing
    0.49
     analyzers
    0.48
     preliminary
    0.46
     synchronously
    0.46
     server
    0.45
     monitoring
    0.45
     scientists
    0.44
     asynchronous
    0.44
     distributed
    0.44
    Activations Density 0.000%

    No Known Activations