© 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. 13-GEMMASCOPE-2-RES-65K
    7. 612
    Prev
    Next
    INDEX
    Explanations

    analogies starting with imagine or you

    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_13_width_65k_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
     ​​
    0.71
     afer
    0.70
     inscrib
    0.64
    andr
    0.62
    maybe
    0.62
                                   
    0.61
    refer
    0.61
     приме
    0.60
    ↵
    0.60
    emplo
    0.59
    POSITIVE LOGITS
    ヴァ
    1.42
     gadis
    1.38
    ヴォ
    1.37
     コットン
    1.37
     犬
    1.37
     バー
    1.36
     siswa
    1.36
     ヴィ
    1.36
    <unused1531>
    1.35
    ガ
    1.35
    Activations Density 0.970%

    No Known Activations