© 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. 83654
    Prev
    Next
    INDEX
    Explanations

    categories followed by specific items

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

    explanation, curiosity, offering

    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
    Ꮈ
    0.45
     portug
    0.42
     spain
    0.42
    OGRAPH
    0.41
     ui
    0.40
     tils
    0.40
    ibilities
    0.39
    +]
    0.39
    vere
    0.39
    ppins
    0.39
    POSITIVE LOGITS
    growing
    0.46
    デビュー
    0.45
    stl
    0.45
    getElementsBy
    0.44
     ጥቅም
    0.44
    キャスト
    0.44
     ripening
    0.44
    turbulence
    0.43
     성장
    0.42
     trồng
    0.41
    Activations Density 0.001%

    No Known Activations