© 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. 4791
    Prev
    Next
    INDEX
    Explanations

    smart, spider, vector, regular, or, true

    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
     판
    1.47
     고민
    1.43
     dude
    1.41
    PLANE
    1.33
    guy
    1.31
     PLANE
    1.26
     npc
    1.26
     괴
    1.24
    ᴘ
    1.24
     色
    1.24
    POSITIVE LOGITS
     larga
    1.10
     largo
    1.01
     stric
    0.99
     parfait
    0.96
     numerosos
    0.95
    вши
    0.94
     compris
    0.93
    sized
    0.91
     vast
    0.91
     centena
    0.91
    Activations Density 0.000%

    No Known Activations