© 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. 164300
    Prev
    Next
    INDEX
    Explanations

    data are

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

    no moat and neither

    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
    但
    0.58
    ה
    0.57
    া
    0.51
     لیکن
    0.50
    কিন্তু
    0.48
    <0x91>
    0.48
    but
    0.48
    نی
    0.47
    <0xBF>
    0.47
    但他
    0.47
    POSITIVE LOGITS
     mayores
    0.53
     schne
    0.51
     energi
    0.50
    jähr
    0.49
     Rey
    0.46
     filmm
    0.46
    produktion
    0.45
     propriété
    0.45
     Energi
    0.45
     Reyn
    0.45
    Activations Density 0.001%

    No Known Activations