© 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. 53095
    Prev
    Next
    INDEX
    Explanations

    hinting curiosity rotor loops goals beyond

    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
    ორი
    0.51
     ವಿ
    0.47
     Се
    0.45
     Татьяна
    0.45
    Collectible
    0.44
    Christina
    0.44
    台
    0.43
     BTC
    0.42
    值的
    0.42
     Christina
    0.42
    POSITIVE LOGITS
    gger
    0.49
     ważne
    0.46
     mirip
    0.41
     orchards
    0.40
     juguetes
    0.40
     jugó
    0.40
     painkillers
    0.40
     anch
    0.40
     mares
    0.40
     ');
    0.39
    Activations Density 0.004%

    No Known Activations