© 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. 36667
    Prev
    Next
    INDEX
    Explanations

    achieve alignment

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

    Data-Oriented Design

    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
    с
    0.55
    ප
    0.55
    ك
    0.54
    ч
    0.53
    ل
    0.52
    غ
    0.51
    أي
    0.50
    К
    0.49
    س
    0.49
    دي
    0.48
    POSITIVE LOGITS
     ミニ
    0.51
     ಮಾಡಿದ
    0.49
     ประ
    0.49
     물질
    0.48
     hyvin
    0.48
    മാര്‍
    0.46
     המש
    0.46
     これ
    0.46
     国
    0.46
     mistress
    0.46
    Activations Density 0.000%

    No Known Activations