© 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. 142859
    Prev
    Next
    INDEX
    Explanations

    browsing streams come with

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

    specialized abilities and functions

    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
     ladders
    0.43
    Eureka
    0.43
    cooked
    0.42
    Percent
    0.42
    كره
    0.41
    旧
    0.41
    MARY
    0.41
     towels
    0.41
    displays
    0.41
     menerapkan
    0.41
    POSITIVE LOGITS
    на
    0.48
    𝑟
    0.45
     Subcommittee
    0.44
     συνεχ
    0.44
    ссер
    0.43
     RECORD
    0.42
     ชีวิต
    0.41
     დიდ
    0.40
     gaan
    0.40
     subunit
    0.40
    Activations Density 0.001%

    No Known Activations