© 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. 129300
    Prev
    Next
    INDEX
    Explanations

    Hidden Charges

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

    bloom might, companies might, showcase muscle, prominently labeled, champion green, wasn't necessarily, roots growing

    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
    not
    0.55
    旅
    0.50
    dag
    0.47
     determinado
    0.47
     fabricating
    0.46
    "$
    0.46
    建造
    0.46
    rat
    0.46
    tidak
    0.46
    定量
    0.45
    POSITIVE LOGITS
     uzyska
    0.53
     nighttime
    0.48
     වල
    0.47
    레
    0.47
     niż
    0.45
    isu
    0.45
    ੪
    0.44
    则是
    0.43
     Aids
    0.43
     Cosmetics
    0.43
    Activations Density 0.001%

    No Known Activations