© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    prepare script

    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
    rinsic
    1.68
    .??
    1.50
    ogany
    1.48
    <end_of_image>
    1.46
    寅
    1.46
     ¿?
    1.44
    าตุ
    1.43
     pedest
    1.41
    ׃
    1.40
     принад
    1.39
    POSITIVE LOGITS
     diarrhoea
    1.37
     calving
    1.33
     cataract
    1.33
    Councillor
    1.28
    ือน
    1.26
     arranges
    1.25
     illness
    1.24
     her
    1.24
    تك
    1.24
    жении
    1.23
    Activations Density 0.065%

    No Known Activations