© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59149
    Prev
    Next
    INDEX
    Explanations

    DHARMa psychopharmacology Pharmacodynamic Spreadsheet

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

    Buddhist and Sanskrit terms, especially "dharma" and related phonetic variations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -3.17
    CurtirCurtir
    -2.98
    䊏
    -2.67
    螣
    -2.58
    絎
    -2.45
    Ⴈ
    -2.41
    玙
    -2.36
     maravill
    -2.34
     but
    -2.34
    有好
    -2.33
    POSITIVE LOGITS
    <td>
    2.59
    </td>
    2.50
    }$
    2.39
    2.34
    ”
    2.30
    ↵↵
    2.19
    但
    2.14
    </
    2.11
     began
    2.11
    se
    2.09
    Activations Density 0.004%
    No Known Activations