© 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. 239203
    Prev
    Next
    INDEX
    Explanations

    storage, oven, baskets, humidity

    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
     inconspicuous
    0.50
     wrongdoing
    0.49
    酛
    0.47
     chemokine
    0.47
    ndown
    0.46
     everytime
    0.46
     soups
    0.45
    BSData
    0.45
     ambiguity
    0.44
     undetected
    0.44
    POSITIVE LOGITS
    ー
    0.53
    č
    0.48
    靠
    0.48
    <0xEA>
    0.47
    è
    0.47
     partir
    0.46
     presso
    0.44
    ঠ
    0.44
    ek
    0.44
     depender
    0.44
    Activations Density 0.000%

    No Known Activations