© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100612
    Prev
    Next
    INDEX
    Explanations

    religious offerings and veins

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

    chain of subjects

    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
    November
    0.46
    マーケット
    0.46
    を知
    0.46
    的人生
    0.44
     chronicle
    0.44
    χρο
    0.44
    경
    0.44
     dépenses
    0.43
    न
    0.43
    čina
    0.42
    POSITIVE LOGITS
     tipped
    0.51
    tipped
    0.48
     forState
    0.45
     tét
    0.44
    alus
    0.43
    拽
    0.43
     grouped
    0.42
    awa
    0.42
    Uploading
    0.41
    </tbody>
    0.41
    Activations Density 0.002%

    No Known Activations