© 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. 89038
    Prev
    Next
    INDEX
    Explanations

    academic and technical contexts

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

    negative or qualifying phrases followed by explanations

    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
     ফু
    0.52
    ня
    0.47
    ma
    0.46
    夸
    0.46
    ྗ
    0.46
     फ्रांस
    0.46
    }(\
    0.45
     முன்பு
    0.44
    다
    0.44
    XS
    0.44
    POSITIVE LOGITS
     collegiate
    0.44
     strictement
    0.44
     populous
    0.43
     Studium
    0.43
     sabbam
    0.43
     Pentium
    0.42
     مستقل
    0.42
     adolescents
    0.41
    を行う
    0.41
     শিক্ষিত
    0.40
    Activations Density 0.003%

    No Known Activations