© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23241
    Prev
    Next
    INDEX
    Explanations

    text display

    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_all/layer_41_width_262k_l0_big
    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
    sendCommand
    0.46
    يطان
    0.39
     actuation
    0.39
     பரிந்து
    0.38
     pooled
    0.38
     سلسلہ
    0.38
    興
    0.38
     хү
    0.37
    toggler
    0.37
    िस
    0.36
    POSITIVE LOGITS
     text
    1.31
     Text
    1.30
    text
    1.20
    Text
    1.19
     texto
    1.16
    文字
    1.16
     текст
    1.14
     texte
    1.11
     tekst
    1.07
    文本
    1.06
    Activations Density 0.005%

    No Known Activations