© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8423
    Prev
    Next
    INDEX
    Explanations

    handling specific cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    1.30
    ları
    1.22
    ların
    1.19
    larına
    1.16
     as
    1.05
    aría
    1.01
    𝗯
    0.98
     hạ
    0.96
    sellers
    0.95
    asına
    0.93
    POSITIVE LOGITS
    -
    1.30
    al
    1.20
    /
    1.18
    (
    1.15
    ’
    1.13
     Handle
    1.12
    T
    1.12
    π
    1.12
    ל
    1.12
    ור
    1.10
    Activations Density 0.036%

    No Known Activations