© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11453
    Prev
    Next
    INDEX
    Explanations

    phrases like "twice as"

    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
     createState
    2.11
    ⁢</
    2.06
     introvert
    1.95
    locatorType
    1.92
    εν
    1.92
     সুইড
    1.91
     프랑
    1.91
     activeButton
    1.91
    <unused1683>
    1.90
     新款
    1.88
    POSITIVE LOGITS
     T
    1.54
    اء
    1.47
    aug
    1.45
    ಡ್
    1.42
     arro
    1.42
    ed
    1.38
    ãos
    1.37
    ेड
    1.36
     stumps
    1.35
    ओं
    1.35
    Activations Density 0.000%

    No Known Activations