© 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. 234120
    Prev
    Next
    INDEX
    Explanations

    French Hairstyle

    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
    Hfn
    0.47
     sous
    0.46
     Danach
    0.45
    wounded
    0.45
    ৮
    0.44
     προς
    0.44
    畄
    0.44
     nặng
    0.44
    sous
    0.44
    ৫
    0.44
    POSITIVE LOGITS
     temptations
    0.50
    语义
    0.45
     chanting
    0.43
     antifungal
    0.43
    algia
    0.42
     chica
    0.42
    ਿਲ
    0.42
    ਾਰ
    0.42
     cages
    0.41
    ula
    0.41
    Activations Density 0.001%

    No Known Activations