© 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. 928
    Prev
    Next
    INDEX
    Explanations

    repeat or another

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

    another or repeat

    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
     ખાસ
    0.46
    ⦖
    0.46
     نها
    0.44
    畞
    0.44
    <unused277>
    0.44
     सॉफ्टवेयर
    0.43
    睄
    0.43
    
    0.42
    כּ
    0.42
    হে
    0.41
    POSITIVE LOGITS
     erneut
    1.48
     another
    1.41
     повто
    1.38
     दोबारा
    1.37
    再度
    1.36
     دوبارہ
    1.35
     repeat
    1.34
    再び
    1.32
     ANOTHER
    1.30
    再次
    1.28
    Activations Density 0.373%

    No Known Activations