© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8794
    Prev
    Next
    INDEX
    Explanations

    legal, paralegal, tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     واذا
    1.24
     المرا
    1.20
    นิด
    1.18
    ህ
    1.18
     liczba
    1.15
    ان
    1.14
    ومن
    1.14
     centimetres
    1.13
     üzerinden
    1.13
    لل
    1.13
    POSITIVE LOGITS
     Daarom
    1.73
    ни
    1.35
    й
    1.32
     Algun
    1.30
    ленного
    1.22
    かった
    1.20
     상황
    1.19
     afirmar
    1.19
    DEPLOY
    1.19
    ses
    1.17
    Activations Density 0.004%

    No Known Activations