© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44730
    Prev
    Next
    INDEX
    Explanations

    visually appealing

    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
     män
    0.44
     mężczy
    0.42
    殞
    0.42
     vro
    0.42
     deck
    0.41
     ross
    0.41
     ura
    0.41
     vermeiden
    0.41
     gilt
    0.41
     pts
    0.40
    POSITIVE LOGITS
    tidak
    0.51
    ，
    0.50
     تازہ
    0.46
     clocked
    0.45
    ಿಸಿದೆ
    0.44
    não
    0.44
     photographed
    0.43
     chased
    0.42
     ngày
    0.42
     uncompromising
    0.42
    Activations Density 0.005%

    No Known Activations