© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    describing what something is

    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
    分开
    0.35
    讫
    0.34
     aident
    0.34
     fraternity
    0.33
     помогут
    0.31
     جلوگیری
    0.31
    续
    0.30
    ուս
    0.30
     nari
    0.30
    鹬
    0.30
    POSITIVE LOGITS
     contains
    0.79
     occupies
    0.78
     possesses
    0.77
     represents
    0.74
     corresponds
    0.72
     behaves
    0.72
     contain
    0.69
     occupy
    0.68
     consists
    0.66
     behave
    0.65
    Activations Density 0.133%

    No Known Activations