© 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. 14564
    Prev
    Next
    INDEX
    Explanations

    colloid silver

    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
     actionBar
    2.14
    WriteLine
    2.13
     दोहरा
    2.12
    立て
    2.01
     ചെയ്തു
    2.01
     eriş
    1.99
    交
    1.96
    钥匙
    1.95
    靂
    1.95
     ചെയ്യ
    1.94
    POSITIVE LOGITS
    ल
    2.99
    ing
    2.36
    MLE
    2.26
    ingh
    2.23
    aient
    2.20
    न
    2.18
    น
    2.16
    ی
    2.13
    लू
    2.08
    cient
    2.08
    Activations Density 0.001%

    No Known Activations