© 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. 157
    Prev
    Next
    INDEX
    Explanations

    virtual meetings

    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
    Anti
    1.65
    Equality
    1.56
     incênd
    1.54
    壹
    1.54
     imagenes
    1.54
    DEAD
    1.52
    DidLoad
    1.50
    дем
    1.49
    Sai
    1.48
    REMOVE
    1.47
    POSITIVE LOGITS
    ে
    1.26
    يّ
    1.21
     maz
    1.19
    tı
    1.18
    siz
    1.16
    विक
    1.13
    يًا
    1.12
    sma
    1.10
    <unused2213>
    1.09
     chron
    1.07
    Activations Density 0.000%

    No Known Activations