© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1011
    Prev
    Next
    INDEX
    Explanations

    in Development or level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     pavimento
    1.50
    uleux
    1.45
    ⃛
    1.44
    τουργ
    1.40
     flooring
    1.39
    ZIE
    1.34
    NESDAY
    1.33
    sph
    1.30
     yearling
    1.30
     faceted
    1.30
    POSITIVE LOGITS
    r
    1.51
    ্ধু
    1.47
    כם
    1.47
    komst
    1.47
    forced
    1.44
    clusions
    1.41
    Ⲕ
    1.39
    рка
    1.35
    гиз
    1.35
    勢
    1.34
    Activations Density 0.637%

    No Known Activations