© 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. 228643
    Prev
    Next
    INDEX
    Explanations

    interests, expertise, from Alibaba, anti-bullying

    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
     নিউজ
    0.50
     DIGITAL
    0.49
    ੁੰ
    0.48
     parler
    0.48
    ലിയ
    0.47
    デジタル
    0.47
    ᒐ
    0.46
     MÉ
    0.46
     variável
    0.46
     HOURS
    0.46
    POSITIVE LOGITS
     Aden
    0.51
    Parameteri
    0.44
    ErrorInfo
    0.44
     Bead
    0.44
     Văn
    0.43
    Annotation
    0.43
    Aden
    0.43
     Bacter
    0.42
    Addr
    0.42
     Anspr
    0.42
    Activations Density 0.001%

    No Known Activations