© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182003
    Prev
    Next
    INDEX
    Explanations

    listen to, believes in, check attach, clarity, Thu Dec, topical and

    np_acts-logits-general · gemini-2.5-flash-lite

    altruism, Four-time, Linear regression, this is, %

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    л
    0.54
    ม
    0.54
    ล
    0.53
    し
    0.52
    손
    0.50
     contenders
    0.50
    ม่า
    0.50
    ྵ
    0.50
     PROTECTION
    0.49
    철
    0.49
    POSITIVE LOGITS
    section
    0.53
     قامت
    0.52
    éra
    0.51
    frac
    0.50
     قام
    0.49
    žen
    0.47
    9
    0.47
    vidia
    0.47
    meida
    0.46
    eem
    0.46
    Activations Density 0.001%

    No Known Activations