© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    degrees and temperature

    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
    ,
    1.66
     a
    1.45
     saraf
    1.13
    ت
    1.13
     adenocarcinoma
    1.07
    ם
    1.04
     bipartite
    1.03
     astrophysics
    1.03
     ardent
    1.01
     embankment
    1.01
    POSITIVE LOGITS
    ot
    1.95
    на
    1.68
    و
    1.68
    ’
    1.66
    ın
    1.63
    ib
    1.50
    在
    1.50
    u
    1.47
    4
    1.46
    for
    1.42
    Activations Density 0.045%

    No Known Activations