© 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. 95681
    Prev
    Next
    INDEX
    Explanations

    Police spokesman, theoretical objects

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

    deprives, Chemical, closely, ferret

    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
    胸
    0.48
     吸
    0.47
    議論
    0.47
    ----------------
    0.45
     ゆっくり
    0.45
     色
    0.45
    予測
    0.45
     斜
    0.45
     transducer
    0.44
    広い
    0.44
    POSITIVE LOGITS
    çı
    0.45
     către
    0.44
    koliko
    0.43
     çocuğ
    0.42
     respectivement
    0.42
    followlike
    0.42
     kā
    0.40
     bunların
    0.39
    çi
    0.39
    öyle
    0.38
    Activations Density 0.000%

    No Known Activations