© 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. 193909
    Prev
    Next
    INDEX
    Explanations

    paths and links

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

    understanding paths and information

    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
     piece
    0.43
    вку
    0.43
    ٧
    0.42
     beurre
    0.42
     intervened
    0.41
    랬
    0.41
     calendario
    0.40
    =\"
    0.40
    लाब
    0.40
    עים
    0.40
    POSITIVE LOGITS
    PATH
    0.55
     PATH
    0.50
     Resol
    0.50
    ojas
    0.49
     Γερμαν
    0.49
     Δη
    0.49
    経路
    0.49
     дорогу
    0.48
     பாதை
    0.47
     Scholarships
    0.47
    Activations Density 0.000%

    No Known Activations