© 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. 154158
    Prev
    Next
    INDEX
    Explanations

    International Journal of

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

    เรีย, ij

    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
     cultivés
    0.47
    牞
    0.45
    閲
    0.45
     conducta
    0.43
    繰り返
    0.42
    }\|_{
    0.42
    ńskim
    0.42
    하라
    0.41
     行っ
    0.41
    পতি
    0.41
    POSITIVE LOGITS
     Bij
    0.55
     tij
    0.54
     Mijn
    0.49
     ij
    0.45
     correspondingly
    0.45
     annotation
    0.44
     i
    0.41
     bij
    0.41
    bij
    0.40
    aan
    0.40
    Activations Density 0.008%

    No Known Activations