© 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. 97266
    Prev
    Next
    INDEX
    Explanations

    sports statistics including ERA

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

    rule-based systems

    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
     PCR
    0.46
     대비
    0.45
     लीजिएगा
    0.45
     Contribute
    0.45
    饬
    0.45
     అంశ
    0.44
     Drinfeld
    0.44
     Webinar
    0.43
     세포
    0.43
     CG
    0.42
    POSITIVE LOGITS
    Afghanistan
    0.52
    adă
    0.51
    LIN
    0.50
    2
    0.50
     শাজ
    0.50
    Wheel
    0.48
    ArrayAdapter
    0.47
    Template
    0.47
    Bangladesh
    0.47
    LIKE
    0.46
    Activations Density 0.001%

    No Known Activations