© 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. 170094
    Prev
    Next
    INDEX
    Explanations

    control group or quantity

    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
    鍬
    0.53
     testaceis
    0.52
    নাথ
    0.51
    lbrakk
    0.50
     oftent
    0.49
    𒀯
    0.49
     vudd
    0.49
     mobilier
    0.49
    。\
    0.49
    <0x18>
    0.48
    POSITIVE LOGITS
     flask
    0.44
     PM
    0.43
     дове
    0.43
     ISSN
    0.41
     flasks
    0.40
     PBS
    0.39
     Arithmetic
    0.39
     PSA
    0.39
     PG
    0.38
     markdown
    0.38
    Activations Density 0.001%

    No Known Activations