© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166871
    Prev
    Next
    INDEX
    Explanations

    common phrases following key words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     start
    0.41
    )|^{
    0.40
     typed
    0.40
    ">${
    0.39
     certificación
    0.39
     مالک
    0.39
     $*
    0.38
    сторо
    0.38
     marshmallows
    0.38
     আগুন
    0.38
    POSITIVE LOGITS
    稩
    0.41
     Dartmouth
    0.41
    Kent
    0.40
    Brightness
    0.40
    Kenya
    0.40
    acos
    0.40
    மணிய
    0.40
     Andover
    0.39
    Angle
    0.39
    кати
    0.39
    Activations Density 0.001%

    No Known Activations