© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31703
    Prev
    Next
    INDEX
    Explanations

    width:

    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
    و
    1.71
    ار
    1.34
    특별시
    1.30
     postérieures
    1.25
    א
    1.23
    letzt
    1.22
    рга
    1.21
    ﺗ
    1.19
    я
    1.18
    তের
    1.15
    POSITIVE LOGITS
    ism
    1.52
    up
    1.34
    ou
    1.25
    ła
    1.20
    k
    1.16
     encuentran
    1.14
    ę
    1.13
    orm
    1.10
    ational
    1.09
     اسی
    1.08
    Activations Density 0.000%

    No Known Activations