© 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. 90962
    Prev
    Next
    INDEX
    Explanations

    exception or contrast

    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
     کلب
    0.48
    Рас
    0.48
    ␥
    0.48
    <unused11>
    0.47
    ⨯
    0.47
    مین
    0.47
     」,
    0.47
    ंत
    0.47
     आरएस
    0.47
    ії
    0.46
    POSITIVE LOGITS
    dag
    0.48
     o
    0.47
    …
    0.45
     alterações
    0.44
     incapable
    0.44
     always
    0.43
     ok
    0.43
     insoluble
    0.43
    diag
    0.43
     guesses
    0.43
    Activations Density 0.006%

    No Known Activations