© 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. 56654
    Prev
    Next
    INDEX
    Explanations

    gerunds

    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
    র
    0.86
    на
    0.80
    ের
    0.77
    ی
    0.77
    나
    0.77
     replete
    0.73
    ﺒ
    0.72
     sogen
    0.71
    ಾನ್
    0.71
     charged
    0.70
    POSITIVE LOGITS
    -
    1.15
    ton
    1.12
    redients
    1.05
    <0xA3>
    0.99
    :
    0.87
    +
    0.86
    ,
    0.82
    ting
    0.80
    ly
    0.79
    <0xAC>
    0.75
    Activations Density 0.245%

    No Known Activations