© 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. 96079
    Prev
    Next
    INDEX
    Explanations

    at least

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

    research questions or hypotheses

    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
    、
    0.53
    IndexArray
    0.48
     والف
    0.45
     و
    0.45
     وقت
    0.44
    فا
    0.44
    氣
    0.43
    ،
    0.43
    ETS
    0.43
    公式
    0.42
    POSITIVE LOGITS
     are
    0.58
     gazed
    0.57
     gaze
    0.57
    n
    0.53
     уч
    0.51
     on
    0.48
     socialize
    0.48
     km
    0.48
     provide
    0.47
     gazing
    0.47
    Activations Density 0.000%

    No Known Activations