© 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. 4352
    Prev
    Next
    INDEX
    Explanations

    bold formatting

    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
     is
    0.42
    ografía
    0.38
     น้ำ
    0.33
    ación
    0.32
    ensión
    0.32
    aan
    0.31
    ’
    0.31
    issä
    0.31
     umani
    0.31
    ähne
    0.29
    POSITIVE LOGITS
    p
    0.43
    S
    0.42
    P
    0.39
    ad
    0.38
    h
    0.38
    на
    0.38
    T
    0.38
    G
    0.38
    ও
    0.38
    1
    0.37
    Activations Density 5.022%

    No Known Activations