© 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. 7646
    Prev
    Next
    INDEX
    Explanations

    two minute rule

    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
     fuse
    1.40
    axiom
    1.37
    óng
    1.36
    immutable
    1.34
    أ
    1.33
    ensure
    1.32
    ەکانی
    1.32
    অ
    1.30
     সি
    1.30
    brands
    1.29
    POSITIVE LOGITS
    ehr
    1.64
    tive
    1.62
    eer
    1.47
    eiro
    1.41
    tir
    1.40
    tır
    1.39
    eurs
    1.36
    ে
    1.34
    tura
    1.33
    ી
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.