© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    code or real-world topics

    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
     numerosos
    1.29
    en
    1.24
    래
    1.24
    ן
    1.21
    iva
    1.21
     verm
    1.19
     numerosi
    1.18
     numerosas
    1.17
    CONTACT
    1.17
    :
    1.16
    POSITIVE LOGITS
    <unused1834>
    2.34
    bibfnamefont
    2.31
    <unused1002>
    2.25
    <unused1662>
    2.24
    <unused978>
    2.22
    <unused674>
    2.21
    <unused1780>
    2.20
    <unused358>
    2.17
     Pattes
    2.15
    <unused1791>
    2.15
    Activations Density 0.000%

    No Known Activations