© 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. 347
    Prev
    Next
    INDEX
    Explanations

    identical copies

    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
    ouveau
    2.01
    /"
    1.86
    ligt
    1.78
     ?",
    1.77
     ?"
    1.76
    lige
    1.69
    "，
    1.65
    ാരോഗ്യ
    1.63
    NA
    1.60
    ोड
    1.59
    POSITIVE LOGITS
     ‘
    2.13
    ’.
    1.95
    ؤ
    1.87
    珺
    1.84
    เหล่า
    1.82
     ejecut
    1.80
    kati
    1.80
    暄
    1.76
     evalu
    1.76
     الدور
    1.75
    Activations Density 0.000%

    No Known Activations