© 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. 72226
    Prev
    Next
    INDEX
    Explanations

    loss of interest in activities

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

    loss of interest in things

    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
    V
    0.54
    K
    0.50
    W
    0.50
    D
    0.47
    エス
    0.44
    Trust
    0.44
    wagen
    0.43
    Z
    0.43
    lion
    0.42
     ケ
    0.41
    POSITIVE LOGITS
    дного
    0.52
     обще
    0.46
    纾
    0.46
    记载
    0.45
     পথিক
    0.45
    nextProps
    0.45
    ญี่ป
    0.45
    inputArr
    0.45
     аспек
    0.44
    报考
    0.44
    Activations Density 0.001%

    No Known Activations