© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 86956
    Prev
    Next
    INDEX
    Explanations

    dictionary tailored

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ennemis
    0.50
    [])
    0.48
    png
    0.48
     voisins
    0.48
     світі
    0.45
     enemies
    0.45
     دینی
    0.45
     націона
    0.44
    神社
    0.43
    lé
    0.43
    POSITIVE LOGITS
    mprj
    0.51
    «.
    0.49
    ות
    0.48
    ود
    0.47
     mujhe
    0.46
    ও
    0.46
    ﺘ
    0.45
    ται
    0.45
    ரியா
    0.43
    Ejercicio
    0.43
    Activations Density 0.000%

    No Known Activations