© 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. 13730
    Prev
    Next
    INDEX
    Explanations

    scenario realities time

    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
    Keb
    1.38
    hc
    1.34
    veu
    1.32
    vec
    1.29
     expenditures
    1.29
    consumers
    1.26
    policies
    1.26
    ድ
    1.26
     expectations
    1.24
    ėl
    1.23
    POSITIVE LOGITS
     сто
    1.27
    десят
    1.17
     bada
    1.16
     ta
    1.10
    兮
    1.09
    తిరే
    1.09
     Stuff
    1.07
     Ta
    1.04
     связа
    1.04
    十八章
    1.00
    Activations Density 0.000%

    No Known Activations