© 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. 241968
    Prev
    Next
    INDEX
    Explanations

    digitally remastered, punctual delivery

    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
    ва
    0.50
    стар
    0.48
    グラ
    0.48
    का
    0.47
    好
    0.46
    एस
    0.45
    紆
    0.45
    ク
    0.45
     Memories
    0.44
     तमिल
    0.44
    POSITIVE LOGITS
     ز
    0.54
     verzi
    0.52
     zum
    0.51
     مُ
    0.51
     bestimmten
    0.48
    ede
    0.47
     zwe
    0.47
     لهم
    0.46
     geprüft
    0.46
     revêt
    0.46
    Activations Density 0.000%

    No Known Activations