© 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. 199941
    Prev
    Next
    INDEX
    Explanations

    targeted ads, highest rate

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

    contextual qualifiers

    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
    opaedic
    0.46
    編成
    0.46
    ulae
    0.45
    !
    0.44
     vocabulary
    0.44
     botones
    0.43
     записы
    0.42
     semua
    0.42
     دونوں
    0.42
     Semua
    0.42
    POSITIVE LOGITS
    пили
    0.47
    માં
    0.46
     Lucien
    0.46
    купа
    0.46
    లూ
    0.42
     ARTHUR
    0.42
    在其
    0.42
     అర్జు
    0.42
    Ở
    0.41
    蕖
    0.41
    Activations Density 0.000%

    No Known Activations