© 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. 251420
    Prev
    Next
    INDEX
    Explanations

    especially in, from the

    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
     actief
    0.54
     எழுத
    0.53
     aktif
    0.51
    gll
    0.51
    SCOPE
    0.49
     uitgevoerd
    0.48
    ^{-/-}$
    0.47
     invertebr
    0.46
     tjän
    0.46
     ausgeführt
    0.46
    POSITIVE LOGITS
    म
    0.48
    ت
    0.46
    ים
    0.45
    ed
    0.43
    кой
    0.43
    ཅ
    0.43
     from
    0.42
    Continue
    0.41
     쇼
    0.40
    י
    0.40
    Activations Density 0.000%

    No Known Activations