© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177794
    Prev
    Next
    INDEX
    Explanations

    features of creatures, candy inspired, BB essay

    np_acts-logits-general · gemini-2.5-flash-lite

    emotional connection and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profoundly
    0.51
    nationality
    0.50
    린
    0.47
    ག
    0.47
    려
    0.46
    以下の
    0.46
    낸
    0.45
    裵
    0.45
    भाषा
    0.45
    ρω
    0.44
    POSITIVE LOGITS
     omdat
    0.52
    \'
    0.52
     mivel
    0.47
    ￠
    0.47
     chargers
    0.46
     countertop
    0.46
     hvis
    0.46
    itettura
    0.46
    y
    0.45
     cafeteria
    0.45
    Activations Density 0.000%

    No Known Activations