© 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. 107670
    Prev
    Next
    INDEX
    Explanations

    worth exactly

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

    estimation and summaries

    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
    ğim
    0.46
     условиях
    0.42
    𝟭
    0.41
    މ
    0.41
    ‍♀️
    0.40
     cmds
    0.40
     dilaksanakan
    0.40
    >′
    0.40
     แปล
    0.40
     AVER
    0.40
    POSITIVE LOGITS
     নাও
    0.51
     motore
    0.50
    側
    0.47
     أيضاً
    0.46
    ince
    0.46
     इंग्लंड
    0.45
    DVD
    0.44
    MESSAGE
    0.43
     بقى
    0.43
    MenuBar
    0.42
    Activations Density 0.001%

    No Known Activations