© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 114819
    Prev
    Next
    INDEX
    Explanations

    Bluetooth, Muslim, victory, nodes

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

    contrasting states

    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
     Zon
    0.51
    mniej
    0.48
    氪
    0.45
    宒
    0.45
     Pist
    0.43
    ză
    0.43
     Mec
    0.43
    ográf
    0.43
    ższej
    0.43
     jsonData
    0.42
    POSITIVE LOGITS
    OTHER
    0.55
    I
    0.50
    NORMAL
    0.46
    エラー
    0.45
     complacency
    0.45
     normality
    0.43
    を提供
    0.42
     behandling
    0.42
    懲
    0.42
     soothing
    0.41
    Activations Density 0.000%

    No Known Activations