© 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. 203808
    Prev
    Next
    INDEX
    Explanations

    this episode

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

    budget/basic speakers

    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
     prioritizing
    0.50
     예배
    0.47
     एवरी
    0.46
    🧔
    0.45
     Interfaith
    0.45
     IconButton
    0.44
     ArrayList
    0.44
     aligned
    0.44
    二维
    0.44
    ij
    0.44
    POSITIVE LOGITS
     drowsiness
    0.48
     hintergrund
    0.45
    صدر
    0.45
    9
    0.43
     copia
    0.43
     leth
    0.43
     цены
    0.42
     домаш
    0.41
     monotony
    0.41
     подви
    0.40
    Activations Density 0.001%

    No Known Activations