© 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. 135255
    Prev
    Next
    INDEX
    Explanations

    pay@hotel, letters of reference

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

    installing software or specific items

    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
    १
    0.43
     होत्या
    0.42
    arı
    0.41
    Sek
    0.39
    \_
    0.39
    BINARY
    0.38
    เ
    0.38
    Already
    0.38
     صہی
    0.38
     समग्र
    0.38
    POSITIVE LOGITS
    蚜
    0.48
     Lug
    0.47
     aerodynamics
    0.43
     Mol
    0.42
    薁
    0.42
     afin
    0.42
     backsplash
    0.41
    Tracker
    0.41
     mol
    0.41
     นะ
    0.40
    Activations Density 0.000%

    No Known Activations