© 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. 101859
    Prev
    Next
    INDEX
    Explanations

    Orange light

    np_acts-logits-general · gemini-2.5-flash-lite

    technical and domain-specific terms

    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
    YC
    0.42
     гру
    0.41
    гор
    0.40
    <0x0D>
    0.40
    扇
    0.40
    ！”
    0.39
     то
    0.39
     gru
    0.39
    Мо
    0.39
    リング
    0.39
    POSITIVE LOGITS
     থাকছে
    0.48
     luglio
    0.47
     rád
    0.47
    ²+
    0.46
     kvadrat
    0.46
     caffè
    0.46
    userId
    0.45
     komp
    0.44
     medzi
    0.44
    राकी
    0.44
    Activations Density 0.002%

    No Known Activations