© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37505
    Prev
    Next
    INDEX
    Explanations

    lists and specific examples

    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
    ال
    0.65
    and
    0.51
    invest
    0.51
    ل
    0.50
     inspecting
    0.49
    improve
    0.49
     ivy
    0.48
     meus
    0.48
    symbols
    0.47
    stones
    0.46
    POSITIVE LOGITS
    כם
    0.46
     scie
    0.45
    ők
    0.44
     realizan
    0.43
     réseau
    0.43
     successo
    0.42
    ϩ
    0.42
     статье
    0.41
     Japón
    0.41
     বল
    0.40
    Activations Density 0.000%

    No Known Activations