© 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. 222156
    Prev
    Next
    INDEX
    Explanations

    insurance and services

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

    improve that experience

    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
    ricies
    0.59
    Ahora
    0.52
    ri
    0.51
    น
    0.51
    aient
    0.50
    cij
    0.49
    Stdin
    0.49
    Tiempo
    0.48
     เกี่ยว
    0.48
    法则
    0.48
    POSITIVE LOGITS
    未
    0.52
     un
    0.49
     Hospice
    0.46
     unst
    0.46
     knocking
    0.46
     unavailable
    0.45
     suffered
    0.45
     ideally
    0.44
     competes
    0.44
     minibus
    0.44
    Activations Density 0.000%

    No Known Activations