© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8828
    Prev
    Next
    INDEX
    Explanations

    hope you enjoyed it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crib
    0.99
     respectable
    0.98
     comparable
    0.97
    ‌آ
    0.96
     keyboard
    0.96
    똘
    0.94
     adaptable
    0.93
     rectangular
    0.91
     rese
    0.91
     salon
    0.90
    POSITIVE LOGITS
     опас
    1.30
     Attacks
    1.18
    の為
    1.17
     atacar
    1.16
     ნახ
    1.14
    Threat
    1.12
     embold
    1.11
     Akh
    1.10
     கார
    1.10
    危
    1.09
    Activations Density 0.000%

    No Known Activations