© 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. 30713
    Prev
    Next
    INDEX
    Explanations

    Here's something

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

    here are

    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
     bilayer
    0.45
     metabolismo
    0.45
     diventare
    0.44
    柽
    0.44
    renzia
    0.44
    ذی
    0.43
     mencegah
    0.43
     étape
    0.43
     később
    0.43
     möjligt
    0.43
    POSITIVE LOGITS
    o
    0.64
    a
    0.63
    e
    0.59
    ’
    0.58
    eine
    0.55
    ea
    0.50
    io
    0.49
    ance
    0.48
    ard
    0.46
    r
    0.46
    Activations Density 0.032%

    No Known Activations