© 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. 44319
    Prev
    Next
    INDEX
    Explanations

    following prepositions

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

    gathering/getting labels

    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
    ment
    0.51
    good
    0.49
    ↵↵↵↵
    0.47
    osan
    0.46
    ↵↵
    0.46
    fontein
    0.45
    0.45
     appropriations
    0.45
     latino
    0.45
    -
    0.45
    POSITIVE LOGITS
    Button
    0.49
    Intersect
    0.49
    AutoStabilise
    0.49
     बृहस्पति
    0.48
    甭
    0.48
    Combine
    0.48
     график
    0.48
     দার্শন
    0.47
    SetName
    0.47
    ウィンドウ
    0.47
    Activations Density 0.000%

    No Known Activations