© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11932
    Prev
    Next
    INDEX
    Explanations

    adding something

    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
     Gossip
    2.64
    ्
    2.63
    𝐰
    2.55
    疮
    2.54
    xyplot
    2.53
    Ⓘ
    2.52
    ⓐ
    2.52
    ees
    2.49
     Origami
    2.44
    ⠀
    2.43
    POSITIVE LOGITS
     إليه
    2.52
     insult
    2.52
    𝗱
    2.43
    ্স
    2.41
    ოვნ
    2.39
    й
    2.32
    ოვანი
    2.28
     comand
    2.28
    𝘁
    2.27
    що
    2.25
    Activations Density 0.055%

    No Known Activations