© 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. 135697
    Prev
    Next
    INDEX
    Explanations

    accuracy and evidence

    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
    あ
    0.50
    ה
    0.49
    ان
    0.47
    こ
    0.46
     le
    0.46
     plas
    0.45
     y
    0.45
     del
    0.44
     shew
    0.43
     k
    0.43
    POSITIVE LOGITS
    itimes
    0.51
    atives
    0.49
    ished
    0.49
    achricht
    0.48
    othes
    0.48
    áln
    0.48
    iches
    0.47
    oll
    0.47
     स्पेस
    0.47
    oci
    0.46
    Activations Density 0.000%

    No Known Activations