© 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. 65173
    Prev
    Next
    INDEX
    Explanations

    had with

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

    competitors, strengths, doing well

    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
    ブ
    0.41
    譜
    0.38
    rema
    0.38
    diagram
    0.38
    "],
    0.38
    oser
    0.37
    $",
    0.37
     みんな
    0.37
    embangkan
    0.36
     thận
    0.36
    POSITIVE LOGITS
    ToRemove
    0.44
    ของการ
    0.41
    ในการ
    0.40
     ການ
    0.40
    ర్థిక
    0.40
    𝑬
    0.39
    报价
    0.39
     Това
    0.39
    罅
    0.39
     если
    0.38
    Activations Density 0.002%

    No Known Activations