© 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. 160584
    Prev
    Next
    INDEX
    Explanations

    Jackson Hole

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

    descriptive adverbs and costs

    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
    ByDefault
    0.54
     rikt
    0.50
     withered
    0.48
    DialogWhen
    0.47
    ᾿
    0.46
     Современ
    0.46
    ﺑ
    0.45
    ῾
    0.45
    ‛
    0.44
    }?
    0.44
    POSITIVE LOGITS
    integer
    0.48
    weekly
    0.43
    Pipe
    0.43
    pipe
    0.43
     extensively
    0.42
    ikuti
    0.42
    logout
    0.42
    login
    0.42
    টে
    0.41
     gently
    0.40
    Activations Density 0.000%

    No Known Activations