© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41071
    Prev
    Next
    INDEX
    Explanations

    specialized or travel diversity Inside

    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_31_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
    Tec
    0.45
    edge
    0.44
    ।
    0.44
    扩
    0.42
     drawer
    0.41
    ire
    0.40
    uc
    0.40
    egu
    0.40
    Flash
    0.39
     Pix
    0.38
    POSITIVE LOGITS
    ского
    0.50
    ется
    0.49
    ные
    0.47
    нены
    0.44
    酈
    0.44
     kemudian
    0.43
    ).(
    0.43
     berjudul
    0.43
    辔
    0.42
     bertujuan
    0.42
    Activations Density 0.000%

    No Known Activations