© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135916
    Prev
    Next
    INDEX
    Explanations

    ever line

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

    question/answer context

    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
    坍
    0.46
     subspace
    0.45
    物质
    0.44
     thymus
    0.44
     thirsty
    0.44
     thiên
    0.43
    協
    0.42
     atomizer
    0.42
     天
    0.41
     hypotension
    0.41
    POSITIVE LOGITS
    絓
    0.49
    あん
    0.47
     desenhos
    0.46
     élet
    0.46
     لیګ
    0.45
    and
    0.45
    Jorge
    0.45
     Lopez
    0.44
    lL
    0.44
    life
    0.43
    Activations Density 0.001%

    No Known Activations