© 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. 177981
    Prev
    Next
    INDEX
    Explanations

    starting with specific terms

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

    song lyrics

    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
    장에
    0.55
    장
    0.51
    出産
    0.50
    .’
    0.49
    བ
    0.48
    자
    0.48
    장에서
    0.47
    フード
    0.46
    법
    0.46
    장은
    0.45
    POSITIVE LOGITS
     iniciar
    0.55
     inspirado
    0.47
     אז
    0.45
     inspire
    0.45
    ніше
    0.45
     iniciando
    0.45
     proviene
    0.45
    unshift
    0.44
     باقي
    0.44
     inicia
    0.43
    Activations Density 0.001%

    No Known Activations