© 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. 175739
    Prev
    Next
    INDEX
    Explanations

    achieve or audio format

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

    functions and code

    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
     সর্বত্র
    0.47
    かわいい
    0.46
    andering
    0.46
     દરેક
    0.44
     пласти
    0.44
    🔧
    0.43
    ዝና
    0.42
     встречаются
    0.41
    
    0.41
    🚧
    0.41
    POSITIVE LOGITS
     blockbuster
    0.52
     achieve
    0.52
     famed
    0.50
     audio
    0.50
     telecom
    0.49
     ngram
    0.49
     lucrative
    0.49
     achieves
    0.48
     achieved
    0.47
     telecoms
    0.47
    Activations Density 0.001%

    No Known Activations