© 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. 139210
    Prev
    Next
    INDEX
    Explanations

    types of models or series

    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
    кто
    0.49
    по
    0.49
    нду
    0.46
    Ako
    0.46
    IKA
    0.46
    Database
    0.45
    Jeśli
    0.45
    ш
    0.45
    انوں
    0.44
    Crisis
    0.44
    POSITIVE LOGITS
     sentencing
    0.44
     convict
    0.43
     sentences
    0.43
     tiredness
    0.43
     oscillation
    0.42
    smiley
    0.42
    s
    0.42
     paperwork
    0.41
     oxygen
    0.41
     respiration
    0.41
    Activations Density 0.015%

    No Known Activations