© 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. 151300
    Prev
    Next
    INDEX
    Explanations

    asked him, America that, email DN, problems later

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

    states, recovery, levels

    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
    apal
    0.52
    IPAL
    0.49
    in
    0.49
    osal
    0.47
    ir
    0.46
     يستخدم
    0.43
    hyp
    0.43
    ]$;
    0.43
     ندير
    0.42
    oc
    0.42
    POSITIVE LOGITS
    એ
    0.54
    時間の
    0.50
    ב
    0.50
     VBA
    0.50
     it
    0.50
     Absence
    0.50
    這
    0.50
     lega
    0.49
     Serien
    0.48
     Pane
    0.48
    Activations Density 0.001%

    No Known Activations