© 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. 249064
    Prev
    Next
    INDEX
    Explanations

    designers and developers

    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
    า
    0.46
    грама
    0.46
    ְ
    0.46
    いる
    0.45
     ugy
    0.45
    챔
    0.45
    츨
    0.44
    ग़
    0.43
    ále
    0.42
     Esses
    0.41
    POSITIVE LOGITS
    ıştı
    0.46
     Installed
    0.46
     tinh
    0.46
     ginseng
    0.45
     waterproof
    0.45
     meningkat
    0.44
     nu
    0.43
    pSensor
    0.43
    സ്ത്ര
    0.43
     harem
    0.43
    Activations Density 0.001%

    No Known Activations