© 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. 13570
    Prev
    Next
    INDEX
    Explanations

    circuit diagrams and symbols

    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
    ’
    0.47
    are
    0.44
    To
    0.44
    ars
    0.43
    ’)
    0.43
    We
    0.43
                                   
    0.42
    𝐭
    0.42
    With
    0.42
    {\'
    0.42
    POSITIVE LOGITS
     ہفت
    0.42
     dip
    0.40
     luminosity
    0.40
     روغن
    0.40
     hemolysis
    0.39
     دی
    0.38
     경우
    0.38
     mycop
    0.38
     aldosterone
    0.37
     nitrile
    0.37
    Activations Density 0.051%

    No Known Activations