© 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. 208836
    Prev
    Next
    INDEX
    Explanations

    business casual

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

    transitions 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
    เด
    0.54
    デ
    0.47
    ég
    0.46
    amped
    0.46
    æ
    0.46
     planta
    0.46
    Pro
    0.45
    েই
    0.45
    াম্প
    0.45
    Vend
    0.45
    POSITIVE LOGITS
     تجویز
    0.48
     સુ
    0.47
    参数向量
    0.46
     ἢ
    0.46
     excision
    0.46
     hướng
    0.45
     مالی
    0.45
     చర్చ
    0.44
    mlin
    0.44
     supervisory
    0.44
    Activations Density 0.001%

    No Known Activations