© 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. 15925
    Prev
    Next
    INDEX
    Explanations

    cover with plastic wrap

    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
     而
    1.59
     也
    1.52
     之
    1.51
     进行
    1.46
     把
    1.44
     為
    1.42
     將
    1.42
     如果
    1.41
     學
    1.40
     其中
    1.40
    POSITIVE LOGITS
     Ausstattung
    1.17
     kategorii
    1.16
     roku
    1.11
     Hochzeit
    1.11
     Zahlung
    1.11
     età
    1.09
     rozmi
    1.08
     Januari
    1.07
     Einwilligung
    1.06
     paiement
    1.06
    Activations Density 0.013%

    No Known Activations