© 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. 180515
    Prev
    Next
    INDEX
    Explanations

    want to

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

    mood and feeling

    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
    t
    0.55
    瑾
    0.46
    Ber
    0.45
    ቂ
    0.44
    掀
    0.43
    రంగ
    0.42
     Advis
    0.42
    在
    0.42
    Pers
    0.42
     Palash
    0.42
    POSITIVE LOGITS
    ल्डेन
    0.54
     ഹൈ
    0.53
    utiérrez
    0.52
     島
    0.51
     යා
    0.49
     ஹை
    0.49
    éra
    0.48
     아멘
    0.47
     fillColorSpace
    0.47
    istisch
    0.47
    Activations Density 0.001%

    No Known Activations