© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9937
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios about self

    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
    高性能
    0.89
     nuclear
    0.87
    nuclear
    0.84
     dis
    0.82
    ev
    0.80
    K
    0.80
     Brexit
    0.79
    +
    0.79
    F
    0.79
    Lip
    0.78
    POSITIVE LOGITS
     terug
    1.29
     Yardım
    1.22
     hotiti
    1.22
     באי
    1.21
    <unused861>
    1.17
     Questi
    1.17
    𒄿
    1.17
    <unused866>
    1.16
    <unused196>
    1.16
     =======
    1.16
    Activations Density 0.000%

    No Known Activations