© 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. 20278
    Prev
    Next
    INDEX
    Explanations

    items and places

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

    multi-lingual prompts and structures

    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
     спра
    0.48
    ノ
    0.46
    О
    0.46
     કેરી
    0.43
     Chica
    0.42
    ани
    0.41
    Де
    0.41
    iad
    0.41
    А
    0.41
    ина
    0.40
    POSITIVE LOGITS
     band
    0.43
     tabel
    0.43
     types
    0.43
     맞춰
    0.42
     suffixes
    0.42
    urnya
    0.42
     bands
    0.42
     hasher
    0.42
     tâches
    0.42
     tipos
    0.41
    Activations Density 0.000%

    No Known Activations