© 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-16K
    7. 13632
    Prev
    Next
    INDEX
    Explanations

    value 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_31_width_16k_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
    s
    0.80
    الش
    0.73
    WITH
    0.71
    wavelength
    0.71
    기
    0.71
    り
    0.70
    ാര്‍
    0.69
    ાઇન
    0.67
    which
    0.66
     руководством
    0.66
    POSITIVE LOGITS
     getValue
    1.20
     value
    1.15
     Value
    1.15
     VALUE
    1.09
     hodnot
    1.06
     currentValue
    1.04
     değeri
    1.02
    '
    1.00
     valore
    0.99
     values
    0.96
    Activations Density 0.181%

    No Known Activations