© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55265
    Prev
    Next
    INDEX
    Explanations

    entry timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '[
    0.38
    <unused543>
    0.36
    辯
    0.36
    ቶ
    0.35
     priesthood
    0.33
     testifies
    0.33
     данным
    0.32
    <unused2049>
    0.32
    ธุรกิจ
    0.32
    縝
    0.32
    POSITIVE LOGITS
    ants
    0.36
     Chromium
    0.36
     EOF
    0.34
     NumPy
    0.33
    sees
    0.33
    bitos
    0.32
     Flutter
    0.32
    лож
    0.32
     TensorFlow
    0.32
     ै
    0.32
    Activations Density 0.001%

    No Known Activations