© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 16020
    Prev
    Next
    INDEX
    Explanations

    visa requirements

    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_16k_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
    で
    1.70
    س
    1.54
    ate
    1.44
    arı
    1.41
    keiten
    1.38
    า
    1.34
    ている
    1.31
    ことになる
    1.31
    어
    1.30
    వారి
    1.25
    POSITIVE LOGITS
    ية
    1.17
     parked
    1.16
     brunt
    1.16
     liking
    1.14
     orchestr
    1.13
     evenly
    1.12
     instit
    1.11
     sogen
    1.10
     apportionment
    1.09
     expanse
    1.07
    Activations Density 0.009%

    No Known Activations