© 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. 155
    Prev
    Next
    INDEX
    Explanations

    metric system, it refers

    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
    жки
    1.90
    棄
    1.89
     코
    1.70
    泗
    1.69
    сть
    1.68
    ಸ್ಯ
    1.63
     अजय
    1.63
    리아
    1.61
    
    1.61
    </sub>
    1.60
    POSITIVE LOGITS
     vitam
    1.65
     balancing
    1.64
     dauert
    1.62
    icut
    1.62
     Parliament
    1.58
     Balancing
    1.51
     bristles
    1.50
     whirling
    1.47
     kadar
    1.46
     amyloid
    1.46
    Activations Density 0.000%

    No Known Activations