© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12833
    Prev
    Next
    INDEX
    Explanations

    exponentiation and powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     FY
    1.52
     urgency
    1.44
     \&
    1.43
     Interested
    1.43
     interested
    1.43
     purpos
    1.42
     interest
    1.42
     displayed
    1.40
     inference
    1.38
     和
    1.35
    POSITIVE LOGITS
     புகழ்
    1.44
    כן
    1.41
    благо
    1.38
    sendStatus
    1.37
    諦
    1.36
    伝説
    1.35
    حافظ
    1.35
    พระ
    1.35
     самый
    1.31
    Благо
    1.31
    Activations Density 0.283%

    No Known Activations