© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10106
    Prev
    Next
    INDEX
    Explanations

    royal succession and resource extraction

    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_22_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
    ιβ
    1.14
     fonctionnal
    1.11
     relent
    1.04
    тифика
    0.99
    뗄
    0.98
     congr
    0.98
    苷
    0.97
     ボタン
    0.97
    ειο
    0.97
    KeyboardView
    0.96
    POSITIVE LOGITS
    chend
    0.85
    rame
    0.84
     Original
    0.77
    ཞ
    0.77
    ri
    0.76
     Nato
    0.76
     Rea
    0.75
    न्छ
    0.73
     KER
    0.73
    ulla
    0.73
    Activations Density 0.000%

    No Known Activations