© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135917
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific nouns

    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
    مام
    0.50
     accessibles
    0.46
    बित
    0.44
    ſelf
    0.44
    م
    0.44
    वी
    0.44
    بار
    0.43
    لم
    0.43
    俳
    0.42
    儸
    0.42
    POSITIVE LOGITS
    eningen
    0.45
    
    0.44
    ating
    0.42
    ator
    0.42
     希望
    0.42
     것이
    0.42
    bong
    0.42
     Psic
    0.41
    üte
    0.41
    latego
    0.41
    Activations Density 0.003%

    No Known Activations