© 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. 180806
    Prev
    Next
    INDEX
    Explanations

    option, then, or, consent, sale, until

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

    Bitcoin, Pseudonymous, Limited Supply

    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
    ли
    0.55
    ש
    0.53
    笑
    0.52
    ности
    0.49
    нали
    0.49
    言語
    0.49
    ＝
    0.47
     일부
    0.47
    ("
    0.46
    辯
    0.46
    POSITIVE LOGITS
     atleta
    0.54
     lector
    0.51
     اگلے
    0.48
    athl
    0.47
     트리플
    0.47
    ர்ஸ்
    0.46
     ക്രിക്ക
    0.46
    ğine
    0.45
     تعلمنا
    0.45
     elección
    0.44
    Activations Density 0.000%

    No Known Activations