© 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. 184499
    Prev
    Next
    INDEX
    Explanations

    stainless steel

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

    scattered much more

    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
     【
    0.49
     negotiated
    0.48
     své
    0.47
     कमाए
    0.46
    ＜
    0.45
     Pad
    0.44
     enacted
    0.44
     মিয়া
    0.43
     وزير
    0.43
     ＜
    0.43
    POSITIVE LOGITS
    猶
    0.47
    pulse
    0.45
    otsu
    0.45
    ouch
    0.44
    іл
    0.43
     povos
    0.43
    ूर
    0.42
    हेही
    0.41
    Confusion
    0.41
    ЛИ
    0.40
    Activations Density 0.001%

    No Known Activations