© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203700
    Prev
    Next
    INDEX
    Explanations

    created by or from

    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
     waxes
    0.46
     dusty
    0.46
     pyridine
    0.46
    ους
    0.46
     woven
    0.46
     quantized
    0.45
    묘
    0.45
     quantitatively
    0.45
     quiescent
    0.45
    Revelation
    0.45
    POSITIVE LOGITS
    ভাস
    0.45
     বুঝ
    0.43
    nament
    0.42
    剩
    0.42
    勲
    0.42
    dere
    0.41
    开头
    0.41
    jä
    0.40
     வண்ணப்பூ
    0.40
     Praia
    0.39
    Activations Density 0.000%

    No Known Activations