© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    best practices

    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
    l
    1.70
    er
    1.69
    -
    1.48
    es
    1.45
    en
    1.38
    j
    1.33
    g
    1.30
    no
    1.30
    stand
    1.29
    par
    1.29
    POSITIVE LOGITS
    <unused1224>
    2.71
    <unused1177>
    2.67
    fnamefont
    2.62
    ColorEffects
    2.61
     sasane
    2.60
    preliquidacion
    2.58
    十柒章
    2.58
    十壹章
    2.57
    <unused5>
    2.56
    ufieurs
    2.55
    Activations Density 0.208%

    No Known Activations