© 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. 143327
    Prev
    Next
    INDEX
    Explanations

    clothing, based, psychotherapy, email

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

    limitation or partiality

    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
    ເຂົ້າ
    0.48
    ৱ
    0.45
    ើត
    0.45
    এক্স
    0.44
    ﻋ
    0.43
     unsecured
    0.43
    ເກ
    0.43
    佰
    0.43
     chế
    0.42
    챌
    0.42
    POSITIVE LOGITS
    ster
    0.52
    ros
    0.50
    ř
    0.50
     gesam
    0.49
    igr
    0.49
     brahman
    0.47
    istern
    0.47
    rals
    0.46
     univerz
    0.46
    itteln
    0.45
    Activations Density 0.001%

    No Known Activations