© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11139
    Prev
    Next
    INDEX
    Explanations

    following numbers and actions

    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
    Les
    1.26
     anyhow
    1.16
    中毒
    1.11
    BUTTON
    1.11
    St
    1.06
    扯
    1.06
     toug
    1.06
    '
    1.06
     anyway
    1.06
    Dict
    1.03
    POSITIVE LOGITS
     ceremony
    1.58
     commemorative
    1.44
     trakcie
    1.41
     Ceremony
    1.41
     ceremonies
    1.40
     celebratory
    1.40
     seder
    1.38
    acağız
    1.34
     Ceremon
    1.31
     aşağıdaki
    1.31
    Activations Density 0.000%

    No Known Activations