© 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. 196572
    Prev
    Next
    INDEX
    Explanations

    discussions, numbers, and first wins

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

    navigating the world as a woman

    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
    疖
    0.54
    Ctr
    0.49
    Reminder
    0.49
    Laundry
    0.49
     Direktor
    0.48
    க்கூடிய
    0.48
    లన
    0.47
    蛀
    0.46
     Respons
    0.45
    🐺
    0.45
    POSITIVE LOGITS
     semic
    0.52
     barred
    0.52
     helped
    0.50
    aux
    0.50
     researching
    0.50
     rooting
    0.50
    fecha
    0.49
    ivar
    0.49
    eg
    0.48
    anch
    0.48
    Activations Density 0.002%

    No Known Activations