© 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. 138628
    Prev
    Next
    INDEX
    Explanations

    personal relationship

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

    dwarf stars

    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
     kc
    0.52
    📔
    0.49
    আছে
    0.47
     була
    0.47
     был
    0.46
     ils
    0.45
     mobs
    0.44
    📓
    0.44
     குறிப்பாக
    0.44
    📜
    0.44
    POSITIVE LOGITS
     njemu
    0.48
    riamo
    0.46
    managerpage
    0.46
    ươi
    0.43
    ਾਈ
    0.43
    geber
    0.42
    َى
    0.42
    resi
    0.42
    apanicola
    0.42
    ută
    0.42
    Activations Density 0.000%

    No Known Activations