© 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. 267
    Prev
    Next
    INDEX
    Explanations

    combination

    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
    0
    1.69
    P
    1.10
    ０
    1.01
    D
    1.00
     is
    0.97
    M
    0.97
    4
    0.95
    L
    0.95
     as
    0.90
    year
    0.89
    POSITIVE LOGITS
    트
    1.30
    ant
    1.25
    ת
    1.24
     combinación
    1.22
    at
    1.18
    r
    1.17
    u
    1.17
    ే
    1.16
    는
    1.14
    ات
    1.11
    Activations Density 0.026%

    No Known Activations