© 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. 113041
    Prev
    Next
    INDEX
    Explanations

    sometimes idealcreate complexsurprisinglynot just

    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
    s
    0.58
     to
    0.55
    ים
    0.50
    ের
    0.49
    س
    0.48
    ی
    0.47
    தூ
    0.46
    DOM
    0.46
    。
    0.45
    مل
    0.44
    POSITIVE LOGITS
     Atari
    0.55
     Ат
    0.51
    amaya
    0.49
    amh
    0.49
     snugly
    0.48
    amore
    0.47
    amag
    0.46
    amano
    0.46
    culas
    0.46
     Fokker
    0.46
    Activations Density 0.001%

    No Known Activations