© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 117984
    Prev
    Next
    INDEX
    Explanations

    corresponding question

    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
    ен
    0.56
    elementProp
    0.54
    ланган
    0.52
    ல்
    0.49
    водство
    0.48
     लची
    0.48
    <unused1071>
    0.48
    рующие
    0.48
    <unused411>
    0.47
    <unused222>
    0.47
    POSITIVE LOGITS
    Cup
    0.48
     finals
    0.47
     up
    0.46
     apple
    0.46
     CHAP
    0.46
    ပ
    0.45
    Town
    0.45
     adversity
    0.44
    Apple
    0.44
     settlers
    0.44
    Activations Density 0.000%

    No Known Activations