© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50146
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols

    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_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
    Straw
    0.45
     ट्यूब
    0.39
    Pupp
    0.38
    irão
    0.38
    约
    0.38
     Dressing
    0.37
    𝓽
    0.37
    spedes
    0.37
    啷
    0.37
     كيف
    0.37
    POSITIVE LOGITS
     tranquilo
    0.44
     piatto
    0.40
     Murt
    0.38
    liko
    0.38
    riso
    0.38
     afectado
    0.37
     fingers
    0.36
    erton
    0.36
     кого
    0.36
     unbroken
    0.36
    Activations Density 0.055%

    No Known Activations