© 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. 51548
    Prev
    Next
    INDEX
    Explanations

    projection display

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

    projector onto backdrop

    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
     चम्मच
    0.41
     estil
    0.41
    カウン
    0.41
    箸
    0.41
     Buckeye
    0.40
    耳机
    0.40
    ˜</
    0.39
     terdiri
    0.39
     sidewalks
    0.38
    筷
    0.38
    POSITIVE LOGITS
     projector
    0.53
     projection
    0.53
     curtain
    0.50
    Projection
    0.49
     projections
    0.49
     projectors
    0.48
    projection
    0.46
    幕
    0.46
     Projection
    0.45
    빔
    0.45
    Activations Density 0.060%

    No Known Activations