© 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. 156626
    Prev
    Next
    INDEX
    Explanations

    translation, info, UK, resources

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

    currently favored

    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
    Fols
    0.48
    too
    0.47
    Fence
    0.47
    Bapt
    0.47
    า
    0.47
     też
    0.47
     zwią
    0.46
    ın
    0.45
    тья
    0.45
     după
    0.45
    POSITIVE LOGITS
     გამ
    0.48
     сочи
    0.47
     statically
    0.47
    渙
    0.45
     خلينا
    0.45
    }-\
    0.45
     மாறி
    0.44
    ಅ
    0.44
     उबर
    0.43
     பேசிய
    0.43
    Activations Density 0.000%

    No Known Activations