© 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. 16-GEMMASCOPE-2-RES-262K
    7. 88818
    Prev
    Next
    INDEX
    Explanations

    salicylic acid, Flower Moon, ERISA, Law

    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_16_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
     recesses
    0.61
     spells
    0.58
    I
    0.57
     juveniles
    0.57
     baterías
    0.55
     दंड
    0.55
     finances
    0.55
     hydraulics
    0.54
    ोर
    0.53
    itionen
    0.53
    POSITIVE LOGITS
     as
    0.68
     مؤرشف
    0.56
     have
    0.55
    qtd
    0.55
    s
    0.55
     afferma
    0.54
    িদ্ধ
    0.54
     sayf
    0.54
    browse
    0.52
     astfel
    0.52
    Activations Density 0.000%

    No Known Activations