© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12031
    Prev
    Next
    INDEX
    Explanations

    multiply by 3

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical operations and multiplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     પરંતુ
    0.55
    시오
    0.46
    amot
    0.45
    addena
    0.44
    닭
    0.44
    ukiy
    0.44
    졀
    0.44
    asında
    0.43
    rare
    0.43
    ুনে
    0.43
    POSITIVE LOGITS
    0.58
     with
    0.52
     multiplic
    0.50
     blessing
    0.49
     multiplied
    0.47
     ×
    0.47
     Blessing
    0.45
     multiply
    0.45
     Finn
    0.45
     bears
    0.44
    Activations Density 0.000%

    No Known Activations