© 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-65K
    7. 2314
    Prev
    Next
    INDEX
    Explanations

    to the or a

    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_65k_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
    ator
    2.46
    ف
    2.40
    to
    2.30
    aux
    2.29
    um
    2.26
    acle
    2.25
    ous
    2.25
    ly
    2.22
     presented
    2.19
    ault
    2.16
    POSITIVE LOGITS
    ppling
    3.60
    ppled
    2.82
    ◸
    2.81
    GTUIKit
    2.80
    FileAlignment
    2.78
    TopOf
    2.68
    ٰذا
    2.61
    ্তন
    2.61
    彡
    2.59
     imprime
    2.55
    Activations Density 1.346%

    No Known Activations