© 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. 229221
    Prev
    Next
    INDEX
    Explanations

    guaranteeing quality or assurance

    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
     ¶
    0.53
     з
    0.49
    ",
    0.48
     Iran
    0.48
     вс
    0.48
    ";
    0.48
     ஆகிய
    0.46
     Egyptian
    0.46
     ос
    0.46
     [:
    0.46
    POSITIVE LOGITS
    生日
    0.49
    ктери
    0.47
    anyon
    0.46
    IDING
    0.46
    BRIDGE
    0.46
    的他
    0.46
    קה
    0.45
    ક્ત
    0.43
    لای
    0.43
     بیټ
    0.43
    Activations Density 0.001%

    No Known Activations