© 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. 40-GEMMASCOPE-2-RES-262K
    4. 204556
    Prev
    Next
    INDEX
    Explanations

    places and things

    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_40_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
    ”
    0.44
    "
    0.41
     experiment
    0.37
    we
    0.35
    bac
    0.34
    」
    0.34
     Experiment
    0.34
    няются
    0.34
     uda
    0.34
    釈
    0.34
    POSITIVE LOGITS
    ียด
    0.42
     हरियाणा
    0.41
     före
    0.40
    וק
    0.38
    ිර
    0.38
     referentes
    0.38
     understated
    0.38
     consistently
    0.38
     Haryana
    0.38
    BoxLayout
    0.38
    Activations Density 0.001%

    No Known Activations