© 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. 240894
    Prev
    Next
    INDEX
    Explanations

    rental and time

    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
    ד
    0.50
    ，
    0.49
    Chromatic
    0.45
     implementations
    0.44
     AUTHOR
    0.44
    模拟
    0.43
    యత్
    0.43
    BROW
    0.43
    ה
    0.43
    нала
    0.42
    POSITIVE LOGITS
     وقت
    0.54
     इंतजार
    0.52
     času
    0.49
     braucht
    0.48
     emanc
    0.48
     hogares
    0.46
    ennials
    0.46
     patriotism
    0.45
     זמן
    0.45
    vasion
    0.45
    Activations Density 0.001%

    No Known Activations