© 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. 15439
    Prev
    Next
    INDEX
    Explanations

    legal and policy information

    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
    <i>
    0.54
    <b>
    0.51
    【
    0.49
    on
    0.48
    на
    0.48
    section
    0.46
    大
    0.45
    何
    0.44
     in
    0.44
    is
    0.43
    POSITIVE LOGITS
     apparence
    0.49
     caoutch
    0.48
    wxT
    0.48
     glycolysis
    0.47
     períodos
    0.46
     razones
    0.45
     kötü
    0.44
     hatal
    0.44
     khấu
    0.44
     éviter
    0.44
    Activations Density 0.001%

    No Known Activations