© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55743
    Prev
    Next
    INDEX
    Explanations

    generally describing or starting

    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
    訟
    0.49
    問
    0.47
     мет
    0.46
    ческих
    0.46
    idon
    0.46
    phans
    0.45
    мара
    0.45
    UniqueIdentifier
    0.45
    ANGMAR
    0.44
    дит
    0.44
    POSITIVE LOGITS
     multiplayer
    0.52
     each
    0.47
     Race
    0.46
     Ctrl
    0.45
     Karaoke
    0.44
     PRC
    0.44
     *
    0.43
     Ninja
    0.43
     Cart
    0.43
     screen
    0.42
    Activations Density 0.003%

    No Known Activations