© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    historical context and explanations

    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_40_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
     trigo
    0.50
     invitados
    0.49
     kilometres
    0.46
     querer
    0.46
    を楽し
    0.45
    roga
    0.44
     interesados
    0.43
    鶏
    0.43
    䒩
    0.43
     ため
    0.43
    POSITIVE LOGITS
     (
    0.51
    allelujah
    0.45
     แจ
    0.42
    er
    0.42
     نے
    0.42
     all
    0.42
    swire
    0.41
     aggression
    0.41
     โดย
    0.39
     hefty
    0.39
    Activations Density 0.000%

    No Known Activations