© 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. 459
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline 1-800-662-HELP

    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
    を
    0.76
    ardin
    0.71
    で
    0.70
     insists
    0.70
    ôle
    0.70
    である
    0.69
    が
    0.69
    ،
    0.67
    และ
    0.67
    和
    0.66
    POSITIVE LOGITS
    msqrt
    0.75
    duplicate
    0.72
    Czas
    0.69
     Gesamt
    0.68
     &$
    0.68
    ˂
    0.68
     ganger
    0.68
     불구
    0.66
    th
    0.66
    msup
    0.66
    Activations Density 0.550%

    No Known Activations