© 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. 36148
    Prev
    Next
    INDEX
    Explanations

    no changes or preference

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

    edge and techniques

    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
     renounce
    0.50
     vodu
    0.48
     nguồn
    0.44
     generalize
    0.42
     GetAll
    0.42
     whichever
    0.40
     whoever
    0.40
     듣
    0.40
     phận
    0.39
     giải
    0.38
    POSITIVE LOGITS
    edges
    0.60
    edge
    0.57
     edges
    0.56
     edging
    0.56
    ürich
    0.54
     edged
    0.54
    ómetro
    0.48
    friction
    0.48
     indentation
    0.47
     isometric
    0.47
    Activations Density 0.000%

    No Known Activations