© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1202
    Prev
    Next
    INDEX
    Explanations

    phrase itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zuid
    0.70
     (
    0.67
     আবির্ভাব
    0.66
     South
    0.65
     H
    0.63
    ↵
    0.62
     lograron
    0.62
     humanos
    0.61
     dispositivos
    0.61
    ired
    0.60
    POSITIVE LOGITS
     feel
    0.87
    Become
    0.85
    Feel
    0.83
    <unused956>
    0.81
     ipsum
    0.81
    Being
    0.80
     Feel
    0.80
     FEEL
    0.80
     being
    0.80
     dominating
    0.79
    Activations Density 1.208%

    No Known Activations