© 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. 201361
    Prev
    Next
    INDEX
    Explanations

    Rhodesia, Natal

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

    uncertain timelines, errors, articles, protein, address

    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
    â
    0.49
     次元
    0.49
     ความ
    0.48
     군
    0.48
     สู
    0.47
     軍
    0.46
    s
    0.45
     Cadet
    0.45
     Gentlemen
    0.44
     เส
    0.44
    POSITIVE LOGITS
    و
    0.55
    ام
    0.49
     planas
    0.46
    ម្លៃ
    0.46
    يج
    0.45
     komplex
    0.45
     propagated
    0.44
    ellery
    0.44
    atherapy
    0.44
     plaques
    0.43
    Activations Density 0.001%

    No Known Activations