© 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. 42612
    Prev
    Next
    INDEX
    Explanations

    hidden software messages

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

    dealing with themes

    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
     ಮೊ
    0.47
    ats
    0.46
    ã
    0.44
    i
    0.44
    ührung
    0.42
    ī
    0.42
    ỉ
    0.42
     pö
    0.42
     Союза
    0.42
     тепер
    0.41
    POSITIVE LOGITS
    ⵜ
    0.56
     फड
    0.56
     Danny
    0.54
    داد
    0.52
     Metcalf
    0.52
     excre
    0.52
     recid
    0.51
    掠
    0.51
     escapar
    0.50
    טו
    0.50
    Activations Density 0.000%

    No Known Activations