© 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. 110529
    Prev
    Next
    INDEX
    Explanations

    i'll explain or focus

    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
    Х
    0.49
    ّه
    0.47
     публику
    0.46
    嗯
    0.46
    reiben
    0.46
    жие
    0.45
     réunion
    0.45
    Я
    0.45
     erlä
    0.44
     agreg
    0.44
    POSITIVE LOGITS
    وید
    0.42
    ointing
    0.42
     Sund
    0.41
     Compute
    0.41
     Mathf
    0.41
    ]}{\
    0.40
     compute
    0.40
     detour
    0.40
     ہاتھ
    0.40
    Rotatef
    0.39
    Activations Density 0.004%

    No Known Activations