© 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. 174606
    Prev
    Next
    INDEX
    Explanations

    NIS master

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

    specific vocabulary

    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
     Abbott
    0.51
    ClFN
    0.50
     Abbot
    0.48
     MK
    0.47
     principally
    0.46
     '/
    0.46
     Abb
    0.45
     >=
    0.44
     emphasizes
    0.44
    FIED
    0.44
    POSITIVE LOGITS
    ib
    0.60
    tor
    0.58
    fileTool
    0.55
    oi
    0.49
    aff
    0.49
    io
    0.49
    eux
    0.49
    attacks
    0.47
    ιά
    0.47
    ovana
    0.47
    Activations Density 0.000%

    No Known Activations