© 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. 191420
    Prev
    Next
    INDEX
    Explanations

    classifications and descriptions

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

    analogy and relationships

    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
    <unused17>
    0.57
     छे
    0.55
    <unused35>
    0.53
    <unused83>
    0.51
    ícias
    0.51
    <unused93>
    0.50
    兵庫
    0.50
    čne
    0.50
    顱
    0.49
    <unused49>
    0.48
    POSITIVE LOGITS
     siblings
    0.59
    ed
    0.59
    in
    0.55
     way
    0.54
     qualifiers
    0.53
    \
    0.52
    er
    0.51
    et
    0.51
     relatives
    0.51
     class
    0.50
    Activations Density 0.000%

    No Known Activations