© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17303
    Prev
    Next
    INDEX
    Explanations

    numpy import

    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
    :
    0.51
    すと
    0.44
     actors
    0.43
     environment
    0.42
     posture
    0.42
     ér
    0.42
     clerks
    0.42
    =
    0.42
     direc
    0.41
     Fin
    0.41
    POSITIVE LOGITS
    lerdir
    0.49
    äck
    0.48
    issime
    0.47
    üler
    0.47
    dalam
    0.47
    ielsen
    0.46
    iglio
    0.45
    PhysRev
    0.45
    이고
    0.44
    z
    0.44
    Activations Density 0.002%

    No Known Activations