© 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. 174999
    Prev
    Next
    INDEX
    Explanations

    basic needs and motivation

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

    biological needs and motivation

    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
     最新
    0.45
     eröff
    0.43
    炝
    0.43
    依法
    0.42
    Ornament
    0.42
    钝
    0.42
    后缀
    0.42
     கண்ணாடி
    0.42
    연
    0.42
    瀋
    0.41
    POSITIVE LOGITS
     satisfaction
    0.54
     hunger
    0.54
     Satisfaction
    0.52
     goal
    0.50
     motivational
    0.49
     भूख
    0.49
     satisfies
    0.47
     hypothalamus
    0.46
     प्रेर
    0.45
    satisfied
    0.45
    Activations Density 0.016%

    No Known Activations