© 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. 105843
    Prev
    Next
    INDEX
    Explanations

    Spread, have, build, Scan

    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
     purch
    0.45
    }}(
    0.44
    С
    0.44
     kanye
    0.42
    "></
    0.41
    <0x0D>
    0.40
    Een
    0.40
    א
    0.40
    ኤ
    0.40
    </td>
    0.39
    POSITIVE LOGITS
    ᴙ
    0.58
     気
    0.55
    ियाँ
    0.54
     нә
    0.54
     Accuracy
    0.52
     現
    0.52
    writeToFile
    0.51
     зміни
    0.51
     Thoreau
    0.51
    靗
    0.51
    Activations Density 0.000%

    No Known Activations