© 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. 8399
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
    CreateCharacter
    1.23
    ления
    1.21
    ной
    1.18
    槨
    1.18
    Trimethyl
    1.10
     simplices
    1.09
    เนิน
    1.08
    <0xBB>
    1.08
    ных
    1.07
    ottam
    1.06
    POSITIVE LOGITS
     percentage
    1.06
    e
    1.06
     hours
    1.01
    ℅
    0.99
     monthly
    0.97
     score
    0.97
    hours
    0.97
     %
    0.96
     weekly
    0.95
     opinião
    0.94
    Activations Density 0.003%

    No Known Activations