© 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. 164861
    Prev
    Next
    INDEX
    Explanations

    highest quality, reception, was charged

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

    within its defined

    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
     into
    0.50
     onto
    0.48
     앞으로
    0.46
    üller
    0.46
    ℅
    0.45
    ivia
    0.45
    XS
    0.44
    ita
    0.44
    üler
    0.44
    @
    0.44
    POSITIVE LOGITS
    ي
    0.72
    ليل
    0.58
     druge
    0.55
    ين
    0.52
    لين
    0.50
    ارين
    0.49
    לו
    0.48
    يج
    0.48
    ف
    0.48
    ע
    0.47
    Activations Density 0.000%

    No Known Activations