© 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. 223012
    Prev
    Next
    INDEX
    Explanations

    instagram photos, not responsible

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

    mathematical and technical subjects

    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
    𝟘
    0.52
    Mesh
    0.52
    Favorite
    0.48
     Favorite
    0.48
    丞
    0.48
     favorite
    0.48
    ليه
    0.47
    Sav
    0.46
    ائش
    0.46
     нём
    0.45
    POSITIVE LOGITS
     해석
    0.49
    editing
    0.45
    cultural
    0.43
     previewBuilder
    0.43
    entukan
    0.42
    anay
    0.42
     בפ
    0.41
    餬
    0.41
    ları
    0.41
     எண்
    0.41
    Activations Density 0.000%

    No Known Activations