© 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. 4247
    Prev
    Next
    INDEX
    Explanations

    medium and intermediate levels

    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
     διαφορε
    0.49
    থমে
    0.48
    ᑉ
    0.48
    HOUT
    0.47
    beatCounter
    0.47
    Armstrong
    0.46
     હજાર
    0.46
    Bracelet
    0.45
    лянчук
    0.45
    𝓌
    0.45
    POSITIVE LOGITS
    /
    0.75
    ,
    0.68
     /
    0.64
     ,
    0.62
     and
    0.59
    ،
    0.55
     -
    0.52
     &
    0.52
     or
    0.50
      
    0.49
    Activations Density 0.077%

    No Known Activations