© 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. 465
    Prev
    Next
    INDEX
    Explanations

    pieces of

    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
     a
    1.52
    o
    1.45
    a
    1.41
    لی
    1.30
    IN
    1.19
    se
    1.18
    دی
    1.18
    Y
    1.17
    diversity
    1.16
    ların
    1.13
    POSITIVE LOGITS
    هاي
    1.30
    يه
    1.28
     verwend
    1.24
    ية
    1.20
    يان
    1.20
    اك
    1.15
     gleiche
    1.14
    يرا
    1.13
     يك
    1.13
    所有
    1.11
    Activations Density 0.034%

    No Known Activations