© 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. 169844
    Prev
    Next
    INDEX
    Explanations

    Galatians, Details about

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

    interchangeably, used with a following explanation

    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
     The
    0.50
     Cea
    0.49
    cere
    0.49
     ယ
    0.48
     ferocious
    0.45
     незале
    0.45
     ಮಹ
    0.45
    リア
    0.43
     Tiles
    0.43
     Derbyshire
    0.42
    POSITIVE LOGITS
     gathered
    0.53
    ൩
    0.47
    也能
    0.47
    вате
    0.46
    ণ্ডল
    0.46
    さんも
    0.46
    idlertid
    0.45
     voices
    0.45
    放在
    0.45
    EndZ
    0.44
    Activations Density 0.001%

    No Known Activations