© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3143
    Prev
    Next
    INDEX
    Explanations

    first followed by time, level, aid, person, point, quarter, law, treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     stej
    1.84
     contenido
    1.83
    其中
    1.80
    μέν
    1.78
    儘
    1.73
    เดียวกัน
    1.71
    և
    1.70
    另一
    1.67
    これも
    1.66
    лій
    1.62
    POSITIVE LOGITS
     responders
    2.11
     baseman
    2.02
     timers
    1.95
     Eindruck
    1.86
    principles
    1.83
     mover
    1.81
     impressions
    1.81
    responder
    1.79
    respon
    1.76
    aries
    1.75
    Activations Density 0.219%

    No Known Activations