© 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. 156206
    Prev
    Next
    INDEX
    Explanations

    foreign months

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

    anything after that

    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
     imagining
    0.47
    금
    0.47
     elaboration
    0.47
    km
    0.45
    광
    0.45
    凉
    0.44
    两大
    0.44
    깜
    0.44
    Ma
    0.44
    utables
    0.44
    POSITIVE LOGITS
     темпера
    0.51
     Probleme
    0.47
     быстрее
    0.46
     suficientemente
    0.46
     probleme
    0.45
     fevereiro
    0.45
     президента
    0.45
     hängt
    0.45
     febbraio
    0.44
     посети
    0.44
    Activations Density 0.001%

    No Known Activations