© 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. 172228
    Prev
    Next
    INDEX
    Explanations

    answering questions

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

    dataset processing

    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
    ческих
    0.56
    㒵
    0.56
     Испа
    0.54
    ленных
    0.54
    ﮏ
    0.52
    棪
    0.52
    ित
    0.52
    вающих
    0.51
    си
    0.51
    팽
    0.51
    POSITIVE LOGITS
    gene
    0.45
    :”
    0.42
     n
    0.42
    ju
    0.41
     nis
    0.41
    ji
    0.40
    ̠
    0.40
    :“
    0.40
    organisation
    0.40
     “
    0.39
    Activations Density 0.000%

    No Known Activations