© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34690
    Prev
    Next
    INDEX
    Explanations

    Hermes and Hermeticism

    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_16_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
    '
    1.20
    },
    1.19
    _
    1.15
    ;
    1.06
    <0x0D>
    1.02
    ),
    0.98
    ,
    0.95
    }{
    0.93
    is
    0.93
    _{\
    0.92
    POSITIVE LOGITS
     herm
    1.17
    ח
    1.09
    ס
    1.08
     Herm
    1.03
    い
    1.02
    ก
    1.00
    ură
    0.98
    ג
    0.98
    Herm
    0.96
    า
    0.93
    Activations Density 0.001%

    No Known Activations