© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    continued or paused

    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_9_width_262k_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
    老
    1.40
    ⃣
    1.37
     predominantly
    1.34
     purely
    1.31
    [`
    1.29
     scalable
    1.29
    ̖
    1.28
    𝐚
    1.27
    ‍♀
    1.26
    −
    1.25
    POSITIVE LOGITS
     adjectives
    1.49
     apoi
    1.46
     siguiente
    1.46
     escuch
    1.45
    ி
    1.42
    Ц
    1.39
     bilgi
    1.35
     baixo
    1.35
     Fragen
    1.35
     histor
    1.34
    Activations Density 0.020%

    No Known Activations