© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10224
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and conditions

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

    sexuality, power, vulnerability

    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_40_width_16k_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
    :-)
    0.60
    awesome
    0.51
     awesome
    0.51
    `
    0.51
     ;-)
    0.48
    gam
    0.47
     lame
    0.45
     guy
    0.45
     goto
    0.45
     `
    0.45
    POSITIVE LOGITS
     canonically
    0.55
    缱
    0.52
    🫠
    0.48
    比起
    0.46
    粝
    0.45
    唳
    0.45
     ось
    0.44
    体现
    0.44
    觑
    0.44
    ஸின்
    0.43
    Activations Density 0.101%

    No Known Activations