© 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. 135232
    Prev
    Next
    INDEX
    Explanations

    direction upwards

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

    vida adecuadas, failure, modeling

    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
    øre
    0.50
    ै
    0.46
     लड़ा
    0.45
    ølge
    0.44
    घाडी
    0.44
    ώ
    0.44
    ły
    0.43
    ampilan
    0.43
     تمامی
    0.43
    opportunities
    0.43
    POSITIVE LOGITS
     изба
    0.48
    DependentUpon
    0.47
    業務用
    0.45
    販
    0.44
    nomes
    0.44
    嬌
    0.42
    сем
    0.41
     subclasses
    0.41
     زائدا
    0.40
    ريبا
    0.40
    Activations Density 0.001%

    No Known Activations