© 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. 42834
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and foreign script

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

    History

    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
     проєкту
    0.47
    ː
    0.46
    ʁ
    0.44
     digitalisation
    0.42
     проє
    0.42
     féd
    0.42
     pouces
    0.40
     œuvres
    0.40
     adduct
    0.39
     opérations
    0.39
    POSITIVE LOGITS
    havi
    0.43
     सिर्फ
    0.42
    僟
    0.41
    精力
    0.41
     იქნება
    0.40
     अॅ
    0.40
    всем
    0.40
    ائف
    0.39
    पढ़
    0.39
    ехать
    0.39
    Activations Density 0.014%

    No Known Activations