© 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. 224770
    Prev
    Next
    INDEX
    Explanations

    calligraphic compositions

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

    organizational activities

    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
    فعيل
    0.55
    िएट
    0.54
    羧
    0.54
    ல்க
    0.53
    نيا
    0.52
    carboxylate
    0.51
    اي
    0.50
    엌
    0.49
    藠
    0.49
    نيه
    0.48
    POSITIVE LOGITS
    ’
    0.58
     Inverse
    0.53
     είναι
    0.52
     sejak
    0.49
     adalah
    0.47
     inverse
    0.47
     всё
    0.46
     גדול
    0.46
     основной
    0.45
     приходится
    0.45
    Activations Density 0.000%

    No Known Activations