© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54324
    Prev
    Next
    INDEX
    Explanations

    Egg yolks and the Ship of Theseus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     nemmeno
    0.47
     headlight
    0.46
     hech
    0.46
     तर
    0.45
     pire
    0.44
    ▄
    0.42
     নইলে
    0.42
    nię
    0.42
     ia
    0.41
    ラの
    0.41
    POSITIVE LOGITS
    midd
    0.43
     ভিয়েতনাম
    0.41
    Derivative
    0.40
    subcategory
    0.40
    ન
    0.40
    }
    0.39
    店铺
    0.39
     geographies
    0.38
    ش
    0.38
    in
    0.38
    Activations Density 0.002%

    No Known Activations