© 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. 220448
    Prev
    Next
    INDEX
    Explanations

    when X occurs followed by Y

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

    explaining what is being discussed

    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
    อป
    0.52
    சி
    0.47
    AIRE
    0.47
    люби
    0.44
    -
    0.44
    洒
    0.44
    挺
    0.43
    వేయ
    0.42
    柴
    0.42
    చే
    0.42
    POSITIVE LOGITS
     anter
    0.56
     otros
    0.54
     otra
    0.53
     ar
    0.50
    orifice
    0.50
     der
    0.50
    or
    0.49
     یا
    0.49
     nowego
    0.49
     enige
    0.49
    Activations Density 0.001%

    No Known Activations