© 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. 139232
    Prev
    Next
    INDEX
    Explanations

    agency agents notice album

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

    pre-trained models and definitions

    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
    ub
    0.58
    ной
    0.46
    man
    0.46
    te
    0.46
    ных
    0.46
    諭
    0.46
    ul
    0.45
    Evidence
    0.44
    业
    0.44
    yn
    0.43
    POSITIVE LOGITS
     postaje
    0.53
     mũ
    0.51
     marketers
    0.48
     synchronously
    0.48
     models
    0.48
     modelos
    0.47
     tří
    0.47
     thẳng
    0.47
     kuma
    0.47
     redesigned
    0.47
    Activations Density 0.000%

    No Known Activations