© 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. 4939
    Prev
    Next
    INDEX
    Explanations

    listing numbers and add

    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
     купи
    1.14
     клі
    1.14
     кри
    1.11
    iri
    1.04
    :
    1.04
    焓
    1.04
    )!
    1.04
    )‏
    1.03
    GetKey
    1.03
     กล
    1.02
    POSITIVE LOGITS
     pausing
    1.41
    中华人民共和国
    1.38
    governmental
    1.29
    zovaniyu
    1.25
     wading
    1.23
    bracketing
    1.22
    aos
    1.22
     suspending
    1.21
     broadcasters
    1.21
     Baloch
    1.19
    Activations Density 0.000%

    No Known Activations