© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 75
    Prev
    Next
    INDEX
    Explanations

    actions following "to"

    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_7_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
    The
    1.59
     and
    1.52
    We
    1.50
    of
    1.50
    It
    1.49
     of
    1.49
    ).
    1.45
    )
    1.43
    à
    1.40
    In
    1.38
    POSITIVE LOGITS
    ppling
    2.07
    GORITH
    1.94
    LOTREntity
    1.92
    preliquidacion
    1.88
    gdock
    1.86
    innerApiCalls
    1.86
    spiderX
    1.82
    <unused83>
    1.79
    imcoords
    1.77
    managedbuild
    1.75
    Activations Density 1.767%

    No Known Activations