© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36482
    Prev
    Next
    INDEX
    Explanations

    cognitive function

    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
     autoload
    0.41
    tsó
    0.40
     ducha
    0.39
    iosk
    0.39
     സ്വാതന്ത്ര
    0.39
    wParam
    0.38
    Launching
    0.37
    漑
    0.37
    ウント
    0.37
    徜
    0.36
    POSITIVE LOGITS
     memory
    1.23
    memory
    1.04
     Memory
    1.04
    Memory
    1.03
    記憶
    1.01
    记忆
    1.00
     memória
    0.98
     creativity
    0.97
     memoria
    0.92
    MEMORY
    0.91
    Activations Density 0.025%

    No Known Activations