© 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. 1155
    Prev
    Next
    INDEX
    Explanations

    create or add if not found

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

    default or else

    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
     hepat
    0.45
    طه
    0.42
    營
    0.42
    รง
    0.42
    肌肉
    0.41
    상은
    0.41
    गिर
    0.41
     histological
    0.41
    煙
    0.41
    潁
    0.41
    POSITIVE LOGITS
     else
    0.49
    default
    0.48
    first
    0.48
     primero
    0.47
     first
    0.45
     dracon
    0.45
     también
    0.45
    warning
    0.45
     edhe
    0.44
     terlebih
    0.44
    Activations Density 0.003%

    No Known Activations