© 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. 104036
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    introducing reasons why

    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
    wealth
    0.59
    steelblue
    0.48
    wearing
    0.48
    ＾＾
    0.48
    water
    0.47
    wallet
    0.47
    lieben
    0.47
    Fue
    0.46
    wert
    0.46
    pretty
    0.46
    POSITIVE LOGITS
     tár
    0.44
     procé
    0.44
    စွာ
    0.44
     nhấn
    0.43
     ngược
    0.43
     Motions
    0.43
    一个月
    0.43
     मजि
    0.42
    ა
    0.42
     faisons
    0.42
    Activations Density 0.002%

    No Known Activations