© 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. 61497
    Prev
    Next
    INDEX
    Explanations

    zero, doubt, apology, challenging, perplex

    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
    también
    0.48
    もない
    0.46
    ੯
    0.46
    hots
    0.45
    arquivo
    0.45
    リスク
    0.44
    umbra
    0.44
    yecto
    0.44
    ໃຊ້
    0.44
    쟤
    0.44
    POSITIVE LOGITS
     Hearing
    0.50
     Fold
    0.50
     Tensorflow
    0.48
     Bingham
    0.47
     hearing
    0.46
     Navigation
    0.46
     diel
    0.46
     turbulent
    0.45
     Figure
    0.45
     Blue
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.