© 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. 67188
    Prev
    Next
    INDEX
    Explanations

    specific parts of text

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

    Mirror mirror on the wall

    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
    о
    0.57
     entrap
    0.45
     corre
    0.44
    е
    0.44
    ophenone
    0.43
    OF
    0.42
    oriented
    0.42
    黙
    0.41
    υ
    0.41
    olak
    0.41
    POSITIVE LOGITS
    鿓
    0.52
    Ꮭ
    0.50
    ცია
    0.50
    𝓷
    0.49
    larım
    0.49
    ്ല
    0.47
    ভিশ
    0.47
     شکست
    0.47
    larınız
    0.47
     finals
    0.47
    Activations Density 0.000%

    No Known Activations