© 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-262K
    7. 23815
    Prev
    Next
    INDEX
    Explanations

    blind spots

    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_262k_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
    𝐊
    0.42
    WebpackPlugin
    0.39
    谑
    0.39
    Quiet
    0.38
    uds
    0.38
    unce
    0.38
    quiet
    0.36
    Brist
    0.36
    androidx
    0.36
    anye
    0.36
    POSITIVE LOGITS
     blind
    1.44
    Blind
    1.39
    blind
    1.37
     Blind
    1.34
    盲
    1.16
     blindness
    1.09
     blindly
    1.02
     blinded
    0.99
     blinds
    0.98
     ब्लाइंड
    0.88
    Activations Density 0.003%

    No Known Activations