© 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. 245662
    Prev
    Next
    INDEX
    Explanations

    bamboo grove

    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
     が
    0.54
     化学
    0.52
    ala
    0.50
     沖縄
    0.49
    、
    0.49
    』
    0.47
     hous
    0.46
    บน
    0.45
     塩
    0.45
     シンプル
    0.45
    POSITIVE LOGITS
     Consider
    0.52
     eleições
    0.51
    }.\
    0.50
     consider
    0.50
     estran
    0.50
     autoridades
    0.50
    Consider
    0.48
     محاسبه
    0.48
     autorités
    0.48
    ᱔
    0.47
    Activations Density 0.000%

    No Known Activations