© 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. 88771
    Prev
    Next
    INDEX
    Explanations

    days a week

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

    languages, metrics, emotional needs

    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
    UnderTest
    0.51
     Boiler
    0.49
    edRight
    0.47
    Backend
    0.46
    铮
    0.46
    Patrick
    0.45
    Sale
    0.45
     հետ
    0.44
     Bragg
    0.42
     যোগ্যতা
    0.41
    POSITIVE LOGITS
     世界
    0.49
     ellipsoid
    0.48
     میوز
    0.48
     alleged
    0.47
    셈
    0.46
     charts
    0.46
    TACT
    0.46
     matern
    0.46
     organize
    0.45
     envisage
    0.45
    Activations Density 0.000%

    No Known Activations