© 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. 88293
    Prev
    Next
    INDEX
    Explanations

    approximate measurements or cast stone

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

    approximate or written

    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
     اسماع
    0.50
     angezeigt
    0.50
    t
    0.50
     عربي
    0.46
     عادي
    0.45
     outras
    0.45
     trzec
    0.44
     skala
    0.44
    ファイル
    0.44
     BIN
    0.44
    POSITIVE LOGITS
    <0x97>
    0.45
    ｈ
    0.45
    折
    0.43
    分别为
    0.42
     લગ
    0.41
    plo
    0.40
    ohydro
    0.40
    chtigen
    0.40
    小伙伴
    0.40
    吭
    0.39
    Activations Density 0.001%

    No Known Activations