© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    questions starting with are or does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    稱為
    0.70
     гэ
    0.65
    adikan
    0.61
    Throwable
    0.61
    ствием
    0.61
    нкт
    0.60
     पकड़ा
    0.59
    罫
    0.59
    ன்னு
    0.59
     ffilm
    0.58
    POSITIVE LOGITS
     Does
    4.06
     does
    3.84
    Does
    3.79
     Did
    3.72
     did
    3.64
     Are
    3.56
    Did
    3.50
    Are
    3.30
    does
    3.27
    did
    3.01
    Activations Density 1.177%

    No Known Activations