© 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. 175959
    Prev
    Next
    INDEX
    Explanations

    manufacturer of, captured Charlie, Information intended

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

    Full Responsibility

    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
     ช่วย
    0.49
     ਸਿੰਘ
    0.49
     तोड़
    0.49
     έχουν
    0.47
    ล
    0.47
     decreases
    0.47
     ی
    0.46
     چلے
    0.46
     shì
    0.46
     conseguir
    0.45
    POSITIVE LOGITS
    <0x0D>
    0.54
    immersive
    0.50
    window
    0.47
    couch
    0.46
    第二
    0.46
    Alchemy
    0.46
     বাদ
    0.45
    хода
    0.45
     masked
    0.45
    CBD
    0.44
    Activations Density 0.002%

    No Known Activations