© 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. 128853
    Prev
    Next
    INDEX
    Explanations

    portions, diverse, RB

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

    higher or lower

    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
    *
    0.51
    sprecher
    0.49
    **
    0.46
    ST
    0.43
    vente
    0.43
    Flex
    0.42
    hundred
    0.41
    chakra
    0.41
    férence
    0.41
    smoke
    0.41
    POSITIVE LOGITS
    疡
    0.49
    ம்
    0.48
    追
    0.46
    〆
    0.46
    枠
    0.46
     বলিলাম
    0.45
    ینګ
    0.45
     वगैर
    0.45
     गिवन
    0.45
    登
    0.45
    Activations Density 0.001%

    No Known Activations