© 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. 131092
    Prev
    Next
    INDEX
    Explanations

    kinsmen according to the flesh

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

    differentiated deep

    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
    辗
    0.56
    из
    0.55
    匆
    0.55
    陋
    0.53
    dört
    0.52
    庙
    0.50
    menin
    0.50
    几年
    0.50
    轻易
    0.49
    下来
    0.49
    POSITIVE LOGITS
     tofu
    0.55
     subarray
    0.53
     c
    0.52
     sashimi
    0.51
     video
    0.50
     Dao
    0.50
     is
    0.50
     naan
    0.50
     touching
    0.49
     bf
    0.49
    Activations Density 0.000%

    No Known Activations