© 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. 98193
    Prev
    Next
    INDEX
    Explanations

    offers compelling value

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

    Y axis

    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
    क्टूबर
    0.51
     downloader
    0.50
     টিক্কা
    0.48
    Ἔ
    0.48
    庥
    0.48
     Coronation
    0.47
    Kappa
    0.47
     umowy
    0.47
     Woch
    0.46
    ब्ब
    0.46
    POSITIVE LOGITS
    t
    0.49
    いません
    0.48
    发言
    0.46
     الفق
    0.46
     herv
    0.45
    fahren
    0.42
     alber
    0.41
     Scrub
    0.41
     Brut
    0.40
     تعرف
    0.40
    Activations Density 0.000%

    No Known Activations