© 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. 217741
    Prev
    Next
    INDEX
    Explanations

    counting colors and quantities

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

    you addressing someone

    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
     defenders
    0.48
    gare
    0.47
     mutter
    0.45
     g
    0.44
     (“
    0.44
     mari
    0.43
     indicated
    0.43
     fueled
    0.43
    r
    0.43
     Republicans
    0.43
    POSITIVE LOGITS
    㯎
    0.52
    ôt
    0.52
    ート
    0.51
     kleuren
    0.49
    ết
    0.47
    貉
    0.47
    BorderStyle
    0.46
    ঞ্চলের
    0.46
     teinte
    0.46
     মুদ্র
    0.45
    Activations Density 0.001%

    No Known Activations