© 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. 42244
    Prev
    Next
    INDEX
    Explanations

    need two / both

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

    requires nuanced understanding

    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
    ваются
    0.55
     Pistol
    0.52
     बॉडी
    0.49
     ಹಿಂದ
    0.48
    𝘄
    0.48
    вающей
    0.48
    uestro
    0.48
    櫥
    0.46
     Schwarzenegger
    0.46
    慝
    0.46
    POSITIVE LOGITS
    az
    0.51
    aj
    0.45
    at
    0.44
     ajustes
    0.42
    alert
    0.42
     alertas
    0.41
     agg
    0.41
     excellently
    0.41
    radius
    0.40
     alerts
    0.40
    Activations Density 0.000%

    No Known Activations