© 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. 217727
    Prev
    Next
    INDEX
    Explanations

    enabled for project

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

    documentaries, services, essential categories

    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
     ہے۔
    0.50
     тому
    0.48
     социального
    0.48
    ᕆ
    0.47
     entornos
    0.43
    逅
    0.42
    Ꮟ
    0.42
    狧
    0.41
     parecido
    0.40
     દ
    0.40
    POSITIVE LOGITS
    otimes
    0.51
    tensor
    0.49
    low
    0.43
    ALL
    0.43
    hall
    0.43
    lam
    0.42
    can
    0.41
    lines
    0.41
    possible
    0.41
    antibodies
    0.41
    Activations Density 0.003%

    No Known Activations