© 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. 86473
    Prev
    Next
    INDEX
    Explanations

    Be you

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

    degree, proximity, or emotional state

    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
     EP
    0.48
     EF
    0.48
    ARE
    0.47
    lazy
    0.47
     BEE
    0.46
    0.46
     I
    0.44
     CH
    0.44
     handmade
    0.44
    lari
    0.44
    POSITIVE LOGITS
     पै
    0.58
    енты
    0.50
     الهواء
    0.49
    ал
    0.49
     dedans
    0.48
     сты
    0.48
    ह
    0.47
     प्रोत्साहित
    0.46
    ሎ
    0.46
    萏
    0.46
    Activations Density 0.004%

    No Known Activations