© 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. 122417
    Prev
    Next
    INDEX
    Explanations

    different schools of thought

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

    doesn't change the core nature

    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
     nieve
    0.50
    ie
    0.49
    véd
    0.48
    emitting
    0.47
    y
    0.46
     mưa
    0.46
    vær
    0.46
    kę
    0.45
     oración
    0.45
    vina
    0.45
    POSITIVE LOGITS
     Tabelle
    0.48
    щен
    0.44
    Гра
    0.44
     дос
    0.44
    ЦИ
    0.43
    Лі
    0.43
     Coke
    0.42
    нді
    0.42
     médian
    0.40
    檔
    0.40
    Activations Density 0.001%

    No Known Activations