© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1209
    Prev
    Next
    INDEX
    Explanations

    square root

    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_13_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
    led
    1.63
    ing
    1.50
     ‘
    1.38
    .’
    1.36
    ed
    1.31
    offer
    1.31
    able
    1.28
    فت
    1.26
    zimmer
    1.24
    ado
    1.22
    POSITIVE LOGITS
    ᵏ
    1.90
    ミリー
    1.71
    _^
    1.71
    くん
    1.65
     परसेंट
    1.65
    ૢ
    1.64
    шан
    1.62
    prime
    1.59
    Pam
    1.59
    ୩
    1.58
    Activations Density 0.107%

    No Known Activations