© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 523
    Prev
    Next
    INDEX
    Explanations

    comparisons using than

    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
    ur
    1.32
    에
    1.06
    enia
    0.99
    gic
    0.96
    urk
    0.95
    ﺍ
    0.93
    anic
    0.92
    gum
    0.92
    ر
    0.92
    enge
    0.90
    POSITIVE LOGITS
    殑
    1.40
    ERGY
    1.21
    ─────
    1.20
    ွင်း
    1.20
    IsOpen
    1.17
    OrEqualTo
    1.13
    ------+
    1.12
    ConformanceMode
    1.11
    ⿰
    1.10
    ┄
    1.10
    Activations Density 1.305%

    No Known Activations