© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36052
    Prev
    Next
    INDEX
    Explanations

    intentionally followed by description

    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
    ০০
    1.30
     absoluto
    1.16
     carbono
    1.14
    硋
    1.14
     empez
    1.13
    arnya
    1.10
    hrad
    1.06
    ٗ
    1.05
     aporta
    1.05
     rex
    1.02
    POSITIVE LOGITS
    ли
    1.86
    ת
    1.68
    ки
    1.50
    ీ
    1.46
    на
    1.45
    此之外
    1.45
    ка
    1.42
    циа
    1.40
    ль
    1.38
    ל
    1.38
    Activations Density 0.006%

    No Known Activations