© 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. 26784
    Prev
    Next
    INDEX
    Explanations

    questions, rigor, proof, stadium, team

    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
     luoghi
    0.46
     avulla
    0.45
     svih
    0.45
     stopni
    0.45
    ⏸
    0.44
    湆
    0.43
     avanti
    0.41
    बित
    0.40
     واقعات
    0.40
    جهات
    0.40
    POSITIVE LOGITS
     hernia
    0.46
    1
    0.45
     mammary
    0.43
    0
    0.43
     Object
    0.43
     contamination
    0.42
    2
    0.42
     curd
    0.42
     adipose
    0.42
     fatty
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.