© 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. 69748
    Prev
    Next
    INDEX
    Explanations

    February month names

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

    combat, glandis, fish, chemicals, loss, glass, growth, pilgrims

    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
     possui
    0.52
     antiguo
    0.51
    Historic
    0.51
     tarih
    0.48
    ᶰ
    0.47
     tarihi
    0.46
    Background
    0.46
     niente
    0.45
    럼
    0.45
    FW
    0.45
    POSITIVE LOGITS
    žky
    0.49
     みんな
    0.48
    かもし
    0.47
     บอก
    0.47
     okam
    0.46
     ਇਸ
    0.45
    を務
    0.45
     straks
    0.45
    튿
    0.45
    us
    0.44
    Activations Density 0.000%

    No Known Activations