© 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. 11988
    Prev
    Next
    INDEX
    Explanations

    list of categories

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

    separators followed by specific words

    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
    Ī
    0.63
    ))
    0.49
    veloppement
    0.46
    Ĭ
    0.45
    INA
    0.44
    NIA
    0.44
    NIOS
    0.43
    GI
    0.42
    za
    0.41
    iy
    0.41
    POSITIVE LOGITS
     с
    0.61
     രണ്ട്
    0.59
    <unused1085>
    0.58
     पॉलिटिकल
    0.58
    絣
    0.57
     अराउंड
    0.57
    <unused664>
    0.57
     सहित
    0.56
     सीजीएल
    0.56
     वैल्यू
    0.55
    Activations Density 0.001%

    No Known Activations