© 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. 217228
    Prev
    Next
    INDEX
    Explanations

    legal rights and ownership

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

    specifics about plans and confidentiality

    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
    改进
    0.50
     endpoints
    0.49
     facades
    0.48
    করিয়
    0.48
    骗
    0.47
    行为
    0.46
    गोरि
    0.46
     uygulama
    0.46
    ispens
    0.45
    стой
    0.45
    POSITIVE LOGITS
    that
    0.55
     partake
    0.52
     배경
    0.51
     THAT
    0.48
     있었
    0.46
    Universität
    0.46
     that
    0.46
    Ownership
    0.46
     connaissance
    0.45
     듣
    0.44
    Activations Density 0.000%

    No Known Activations