© 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. 68883
    Prev
    Next
    INDEX
    Explanations

    essential WordPress, Teddy Bear, emphasized that

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

    monitoring auditing actions fluctuations

    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
     Surabaya
    0.53
    øre
    0.52
     pilot
    0.52
     sugary
    0.51
    ಕಾರಿ
    0.50
     bulldoz
    0.50
     conco
    0.48
    ⊇
    0.48
     gooey
    0.47
     usually
    0.47
    POSITIVE LOGITS
     აღმასრულებელი
    0.53
    一来
    0.51
    审
    0.48
    ف
    0.46
     последнее
    0.45
     divergences
    0.45
    و
    0.44
    يع
    0.44
    背
    0.44
    غ
    0.44
    Activations Density 0.000%

    No Known Activations