© 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. 11529
    Prev
    Next
    INDEX
    Explanations

    predicting phrase continuations

    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
    IZA
    0.57
    nian
    0.53
    biet
    0.52
    rá
    0.51
     дзяржа
    0.51
    monds
    0.49
    fonos
    0.49
    މ
    0.48
    rer
    0.48
    court
    0.48
    POSITIVE LOGITS
     whiteboard
    0.49
    غط
    0.47
     salt
    0.47
    什么样的
    0.46
     stub
    0.46
     microw
    0.46
     sel
    0.45
     sun
    0.44
     --
    0.43
     plate
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.