© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128420
    Prev
    Next
    INDEX
    Explanations

    Expectations, correctness, wall, material

    np_acts-logits-general · gemini-2.5-flash-lite

    remove rust and repair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )،
    0.55
    <0x0D>
    0.48
     بنگالی
    0.47
    </h3>
    0.45
    )，
    0.45
     دسته
    0.44
     grafted
    0.43
    )。
    0.42
     عرب
    0.42
    </h4>
    0.41
    POSITIVE LOGITS
     degrading
    0.53
    larını
    0.51
    zigen
    0.51
    အပိုင်း
    0.50
     USGS
    0.50
    ংশে
    0.50
    щите
    0.49
     IEquatable
    0.49
    يارات
    0.49
    дом
    0.48
    Activations Density 0.001%

    No Known Activations