© 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. 55094
    Prev
    Next
    INDEX
    Explanations

    equal, fast, fold

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

    explaining *why*

    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
    俨
    0.57
    ừ
    0.54
    řejmě
    0.52
    стіше
    0.52
    鸬
    0.52
    ômes
    0.52
    闪
    0.52
    और
    0.51
    𝘫
    0.50
    دی
    0.50
    POSITIVE LOGITS
     size
    0.64
     rate
    0.61
     value
    0.60
    ↵
    0.58
     quantitative
    0.56
     numerator
    0.55
     magnitude
    0.55
     individual
    0.54
     qualitative
    0.54
     relative
    0.53
    Activations Density 0.000%

    No Known Activations