© 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. 2187
    Prev
    Next
    INDEX
    Explanations

    specific complex details

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

    abstract concepts and consequences

    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
    ），
    0.22
     fhe
    0.21
     ）
    0.21
    ”。
    0.19
    ）
    0.19
    ）,
    0.19
    ）。
    0.18
     ，
    0.18
     指定
    0.18
     同じ
    0.18
    POSITIVE LOGITS
     intricacies
    0.25
     way
    0.21
     myriad
    0.20
     complexities
    0.20
     impact
    0.20
     multitude
    0.20
     implications
    0.19
     plethora
    0.19
     intric
    0.18
     nuances
    0.18
    Activations Density 2.032%

    No Known Activations