© 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. 105557
    Prev
    Next
    INDEX
    Explanations

    asleep, pity, snooze, crazy

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

    emotions and states

    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
    ляти
    0.53
    ת
    0.53
    חו
    0.52
    не
    0.51
    לא
    0.51
     хотим
    0.50
    }$.
    0.48
    т
    0.47
    ᆫ
    0.47
    ativos
    0.46
    POSITIVE LOGITS
    6
    0.49
    5
    0.49
     Strawberry
    0.45
     Docker
    0.44
     Trường
    0.44
     hầu
    0.44
     Grâce
    0.43
     Leuven
    0.43
     Sites
    0.43
     Dès
    0.43
    Activations Density 0.001%

    No Known Activations