© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109607
    Prev
    Next
    INDEX
    Explanations

    their was

    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
     কখনো
    0.48
     solvation
    0.48
     jederzeit
    0.45
    🔐
    0.44
     Arsen
    0.43
     tannin
    0.42
     chromatin
    0.42
     soldering
    0.41
    ຯ
    0.41
     혼
    0.41
    POSITIVE LOGITS
     –
    0.48
    埸
    0.47
    łasz
    0.45
    ır
    0.44
     cref
    0.43
    學校
    0.43
    rę
    0.42
    </th>
    0.42
     pots
    0.41
     EN
    0.41
    Activations Density 0.001%

    No Known Activations