© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200312
    Prev
    Next
    INDEX
    Explanations

    words after "random"

    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
    ors
    0.48
    ())->
    0.46
    erven
    0.45
    emph
    0.44
    aptic
    0.44
     μαύ
    0.43
    habitude
    0.43
     سیا
    0.43
     significative
    0.43
    (){
    0.42
    POSITIVE LOGITS
    ش
    0.43
     acompanha
    0.43
     call
    0.42
     visitation
    0.41
     equates
    0.40
     company
    0.40
     at
    0.40
    وم
    0.40
     sute
    0.40
     andolan
    0.39
    Activations Density 0.004%

    No Known Activations