© 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. 219403
    Prev
    Next
    INDEX
    Explanations

    questions and opportunities

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

    aws cli commands and spec sheets

    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
     chronically
    0.52
    帙
    0.44
     absc
    0.44
    carbon
    0.43
    ᱯ
    0.43
    ковь
    0.42
    続
    0.42
     extr
    0.41
     contemplated
    0.41
     கார்ப
    0.41
    POSITIVE LOGITS
    uje
    0.51
     efter
    0.51
     všech
    0.50
    owało
    0.50
    ஷ்
    0.50
    ítás
    0.50
        
    0.49
    ็บ
    0.49
     .$
    0.49
    Kako
    0.48
    Activations Density 0.000%

    No Known Activations