© 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. 509
    Prev
    Next
    INDEX
    Explanations

    the largest

    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
     and
    1.41
     that
    1.31
    <0xF3>
    1.20
     because
    1.20
     и
    1.18
     with
    1.18
     a
    1.12
     to
    1.11
    .
    1.10
     in
    1.08
    POSITIVE LOGITS
     sogenannten
    1.01
     sogenannte
    0.95
     její
    0.94
     menghub
    0.92
    밂
    0.92
     gesamte
    0.91
    ğmen
    0.90
     količ
    0.90
     başlayalım
    0.90
     kuidas
    0.89
    Activations Density 2.090%

    No Known Activations