© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    commas used as separators

    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
    0.50
            
    0.40
     />
    0.39
     wind
    0.38
     /
    0.38
     shape
    0.38
     hypers
    0.38
     *
    0.38
     **
    0.37
     "
    0.36
    POSITIVE LOGITS
    .$,
    0.65
    ,</
    0.64
    !,
    0.63
    ‌,
    0.62
    ,[
    0.61
    ,<
    0.61
    ,{\
    0.59
    ,~
    0.58
    ,…
    0.58
    ,
    0.56
    Activations Density 0.026%

    No Known Activations