© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6059
    Prev
    Next
    INDEX
    Explanations

    closing `</body>`

    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
     हृदय
    1.25
    ക്കുള്ള
    1.22
    醮
    1.21
     متجه
    1.21
    வே
    1.19
    שוט
    1.18
     pentru
    1.17
     wę
    1.17
    cü
    1.16
     для
    1.14
    POSITIVE LOGITS
    Congrats
    1.26
    性的
    1.23
    ording
    1.17
     verifiable
    1.16
    appro
    1.15
    性和
    1.14
     noticia
    1.13
    }^{*
    1.11
    лась
    1.11
    Named
    1.11
    Activations Density 0.000%

    No Known Activations