© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14875
    Prev
    Next
    INDEX
    Explanations

    calories per

    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
    cooked
    2.23
    ington
    2.01
     cooked
    1.80
    leurs
    1.79
    یث
    1.74
    a
    1.74
    esley
    1.70
    leur
    1.70
    ie
    1.68
    ক্ষেপে
    1.66
    POSITIVE LOGITS
    轫
    2.41
    origData
    2.29
    Ду
    2.27
     вполне
    2.15
    tabPage
    2.13
    ድን
    2.12
    gameObjects
    2.09
     cea
    2.08
    Uma
    2.07
     quite
    2.07
    Activations Density 0.012%

    No Known Activations