© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 42
    Prev
    Next
    INDEX
    Explanations

    numbers within range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     biographer
    1.19
    ัด
    1.18
     ayudas
    1.15
     dyst
    1.13
     briefs
    1.09
     scenery
    1.09
    条
    1.09
     ambush
    1.08
    rež
    1.08
     rett
    1.07
    POSITIVE LOGITS
     numeric
    1.92
    Numbers
    1.80
     números
    1.78
    number
    1.78
     numeri
    1.78
     숫
    1.77
     숫자
    1.77
     numbers
    1.77
     numer
    1.75
    数字
    1.73
    Activations Density 3.382%

    No Known Activations