© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13011
    Prev
    Next
    INDEX
    Explanations

    without a trace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    ه
    2.93
    i
    2.55
    o
    2.44
    ০
    2.40
    י
    2.14
    ি
    2.10
    ⎣
    2.01
    ம்
    1.96
    ÉE
    1.93
    ი
    1.91
    POSITIVE LOGITS
    加えて
    2.21
     fail
    2.19
     sammen
    2.00
     усі
    2.00
     допомо
    1.98
     însă
    1.96
    ون
    1.96
     względu
    1.95
    платно
    1.94
     Weiter
    1.93
    Activations Density 0.040%

    No Known Activations