© 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. 7-GEMMASCOPE-2-RES-16K
    7. 430
    Prev
    Next
    INDEX
    Explanations

    explaining why it

    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
    s
    1.17
    ie
    0.93
    ات
    0.90
    ’
    0.89
    sé
    0.86
    Z
    0.85
    de
    0.85
    ve
    0.84
    ron
    0.83
    ně
    0.82
    POSITIVE LOGITS
    LOADSTRING
    1.16
     stiffer
    1.09
     cracks
    1.08
     surpluses
    1.08
    LOTREntity
    1.06
     softness
    1.04
     coups
    1.04
    <unused905>
    1.04
     overt
    1.03
    <unused2173>
    1.03
    Activations Density 2.347%

    No Known Activations