© 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. 125790
    Prev
    Next
    INDEX
    Explanations

    properly employed

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

    that, this is, or quoted speech

    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
    ere
    0.49
    ỡi
    0.48
    ünü
    0.47
     parç
    0.46
    번
    0.46
    ürü
    0.45
    प्रदेश
    0.45
    äns
    0.45
    lanır
    0.45
    秋冬
    0.45
    POSITIVE LOGITS
     bahwa
    0.48
     rằng
    0.48
    انية
    0.44
     이건
    0.43
     Sanskrit
    0.42
     لکھا
    0.42
     Kindergarten
    0.42
    nya
    0.41
     Pach
    0.41
    ،
    0.41
    Activations Density 0.001%

    No Known Activations