© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3665
    Prev
    Next
    INDEX
    Explanations

    missing child, missing out, missed calls

    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
    '
    2.40
    ff
    2.32
    ->"
    2.31
     SHORT
    2.29
     confidence
    2.27
    ffine
    2.25
    ishes
    2.22
    লো
    2.20
     sweaters
    2.18
    meros
    2.18
    POSITIVE LOGITS
    𝑒
    2.89
    issippi
    2.78
    𝑙
    2.63
    ять
    2.57
    eyJ
    2.56
    ToShow
    2.56
    𝑢
    2.53
    крыть
    2.51
    ﺔ
    2.49
    issauga
    2.48
    Activations Density 0.070%

    No Known Activations