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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69733
    Prev
    Next
    INDEX
    Explanations

    in a park

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    <img>
    0.88
    /**/*.
    0.87
     PCBs
    0.87
     Matrices
    0.85
     backlinks
    0.83
    auru
    0.82
     결방
    0.78
    ữ
    0.77
     checklists
    0.77
    xFF
    0.73
    POSITIVE LOGITS
     dignity
    2.22
    private
    2.19
    chooser
    2.17
     privado
    2.09
     solace
    2.03
     peace
    2.00
     confidence
    1.99
    وسط
    1.99
     safety
    1.98
     tepl
    1.98
    Activations Density 0.002%

    No Known Activations