© 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. 37731
    Prev
    Next
    INDEX
    Explanations

    operating subsidiary, his mind

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

    asking questions

    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
    ان
    0.47
    Age
    0.45
    ए
    0.45
    شم
    0.45
    The
    0.42
     had
    0.42
    从此
    0.42
     विनय
    0.41
    ي
    0.41
     تح
    0.41
    POSITIVE LOGITS
    șa
    0.52
    navbarSupported
    0.49
    聞いた
    0.46
    landı
    0.46
    ș
    0.46
    uliert
    0.44
    circ
    0.43
    otimes
    0.43
    chevron
    0.43
    ități
    0.42
    Activations Density 0.000%

    No Known Activations