© 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. 38696
    Prev
    Next
    INDEX
    Explanations

    specific terms, phrases, and languages

    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
     หย
    0.46
     vårt
    0.44
    酒
    0.44
     plufieurs
    0.43
    asjonen
    0.41
    รี
    0.41
    律
    0.41
    新聞
    0.41
     vår
    0.41
    öffnung
    0.40
    POSITIVE LOGITS
    сё
    0.47
    این
    0.47
    চরণ
    0.45
    pearl
    0.45
    வசம்
    0.45
     Maud
    0.44
    /*
    0.43
    ᠣ
    0.42
     этом
    0.42
    ঁচ
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.