© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9798
    Prev
    Next
    INDEX
    Explanations

    Adds, indeed, confirmed

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

    ". “

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

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
    Says
    0.43
    :“
    0.43
    .“
    0.41
    をもって
    0.40
     “‘
    0.39
    essero
    0.38
    最后
    0.38
     همچنین
    0.38
     “[
    0.38
     Delaney
    0.38
    POSITIVE LOGITS
     Adds
    0.68
    确实
    0.66
    Adds
    0.64
    Indeed
    0.63
     Indeed
    0.60
    Added
    0.59
     Added
    0.57
    確實
    0.56
     indeed
    0.55
    的确
    0.55
    Activations Density 0.076%

    No Known Activations