© 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. 78825
    Prev
    Next
    INDEX
    Explanations

    advance

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

    recognizing, observe, estimates

    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
    Similar
    0.49
    罩
    0.49
    真空
    0.49
    悖
    0.48
     teorema
    0.47
     തീ
    0.47
     꿈
    0.47
    Klas
    0.46
    菏
    0.46
    不止
    0.45
    POSITIVE LOGITS
     United
    0.42
     Small
    0.42
     elephant
    0.42
    MOBILE
    0.41
     *)$
    0.41
     五
    0.40
     gorilla
    0.40
     eight
    0.40
    ம்பு
    0.40
    PARAM
    0.39
    Activations Density 0.000%

    No Known Activations