© 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. 52337
    Prev
    Next
    INDEX
    Explanations

    positive and factual descriptions

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

    decisions relates cultural positively

    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
    編曲
    0.45
    <b>
    0.43
    Width
    0.42
    BasePath
    0.42
    鎖
    0.42
     batches
    0.41
    INDU
    0.41
    ;
    0.41
    ﾗ
    0.40
     現在
    0.40
    POSITIVE LOGITS
     korrekt
    0.55
     günlük
    0.52
     positif
    0.52
     pozitiv
    0.52
     codzien
    0.52
    েমনি
    0.52
     spôsob
    0.52
     yıld
    0.51
     hyvä
    0.51
     seul
    0.51
    Activations Density 0.000%

    No Known Activations