© 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. 242315
    Prev
    Next
    INDEX
    Explanations

    welcome friends

    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
    േഷ
    0.49
     comprov
    0.48
    arantad
    0.46
     considerare
    0.46
    анг
    0.45
    эх
    0.45
    로운
    0.44
    દ
    0.44
    стоя
    0.43
    ería
    0.43
    POSITIVE LOGITS
     -
    0.49
     #
    0.46
     Hell
    0.46
     ინ
    0.44
     Listening
    0.44
    sa
    0.44
    listen
    0.43
    -)
    0.42
     \
    0.42
     "
    0.41
    Activations Density 0.000%

    No Known Activations