© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46341
    Prev
    Next
    INDEX
    Explanations

    pattern means practical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pistachio
    0.47
     호
    0.47
    5
    0.47
     pă
    0.46
     ris
    0.46
     ô
    0.45
     quinta
    0.44
     Pä
    0.44
     apă
    0.44
     öt
    0.43
    POSITIVE LOGITS
    relse
    0.47
    जिये
    0.46
    zyna
    0.42
    뀐
    0.41
    overset
    0.39
    ترض
    0.39
     Duties
    0.38
    tuples
    0.38
    zur
    0.38
    ifferentiate
    0.38
    Activations Density 0.002%

    No Known Activations