© 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-16K
    7. 12574
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    timeout parameter

    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_16k_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
    barung
    0.48
     स्त्रियों
    0.46
    鎊
    0.41
    പ്പിക്ക
    0.41
     Females
    0.40
     النساء
    0.40
    ிற்கும்
    0.39
     Mitochondrial
    0.38
     Montes
    0.38
     uranyl
    0.38
    POSITIVE LOGITS
     z
    0.44
     з
    0.39
    ?;
    0.38
    @
    0.37
     fer
    0.37
     meters
    0.36
    "
    0.36
     complex
    0.36
     cham
    0.35
     alti
    0.35
    Activations Density 0.080%

    No Known Activations