© 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. 72520
    Prev
    Next
    INDEX
    Explanations

    baseball hits singles doubles

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

    grounding out, OBP, excellent captain

    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
     मैथमेट
    0.44
    鬆
    0.44
    กำ
    0.41
    ेंस
    0.41
     matemática
    0.39
    קס
    0.38
     عبدال
    0.38
    岗
    0.38
     assass
    0.38
    Cuánt
    0.38
    POSITIVE LOGITS
     শ্রবণ
    0.43
    ਾਨ
    0.42
     METAL
    0.42
     Cycles
    0.42
     Ego
    0.41
     ಇದೆ
    0.40
     parrot
    0.40
    竊
    0.40
     বাড়
    0.40
     cellulose
    0.40
    Activations Density 0.073%

    No Known Activations