© 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. 78062
    Prev
    Next
    INDEX
    Explanations

    lists, numbered items, or descriptive phrases

    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
     note
    0.46
     może
    0.46
    児
    0.44
     může
    0.43
    rootDir
    0.42
     Shield
    0.42
    ﺸ
    0.42
    டுக
    0.42
    רום
    0.41
     ශ
    0.40
    POSITIVE LOGITS
    utlich
    0.50
     अधि
    0.50
    កំណ
    0.49
     भएका
    0.48
     tế
    0.47
    umsal
    0.46
     там
    0.46
     splashes
    0.46
    ขา
    0.46
     summits
    0.46
    Activations Density 0.001%

    No Known Activations