© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126708
    Prev
    Next
    INDEX
    Explanations

    unique, authentic, or descriptive narratives

    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
     Without
    0.48
    t
    0.46
     Ferris
    0.46
    ideas
    0.44
     pil
    0.44
     Through
    0.43
    ᱜ
    0.43
     Diaspora
    0.43
     Ideas
    0.42
    tanh
    0.41
    POSITIVE LOGITS
     authentically
    0.58
     centrally
    0.55
     subdue
    0.54
    unico
    0.52
     optimised
    0.50
     centralised
    0.48
     ఒక
    0.47
     المركزي
    0.46
     Центра
    0.45
    し
    0.45
    Activations Density 0.001%

    No Known Activations