© 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. 45458
    Prev
    Next
    INDEX
    Explanations

    introducing information or specifying conditions

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

    for debugging, for each, for example

    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
    П
    0.42
     حقیقت
    0.41
     Hr
    0.39
    REAT
    0.38
    가지
    0.38
    측
    0.38
    全ての
    0.38
    বিস্ত
    0.38
    Ο
    0.37
    鲐
    0.37
    POSITIVE LOGITS
    γγελ
    0.45
     kamera
    0.42
     coupe
    0.42
     അങ്ങനെ
    0.42
     但是
    0.41
     protokol
    0.40
    iriman
    0.39
     เพื่อ
    0.39
     mús
    0.39
     recientemente
    0.39
    Activations Density 0.008%

    No Known Activations