© 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. 145697
    Prev
    Next
    INDEX
    Explanations

    IFYing

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

    .get/Tapped/secret

    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
     intrauterine
    0.46
     vitre
    0.43
     endometri
    0.41
    碱
    0.39
     segmental
    0.38
    かない
    0.38
     ),
    0.37
     buccal
    0.36
    erving
    0.36
     民
    0.36
    POSITIVE LOGITS
    Gesch
    0.46
    ﺼ
    0.45
    getC
    0.43
    gesch
    0.40
     साहस
    0.40
     فإن
    0.38
     हमने
    0.38
    }}$.
    0.38
     জ্যো
    0.38
    当我
    0.38
    Activations Density 0.020%

    No Known Activations