© 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. 130627
    Prev
    Next
    INDEX
    Explanations

    tickets, maximum, Jesus, business

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

    foreign languages and discussions

    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
     CE
    0.50
     BIS
    0.48
    OMBRE
    0.47
    阚
    0.46
     subpar
    0.44
    ∑
    0.44
     BELL
    0.44
     손
    0.44
    CE
    0.44
     tanda
    0.43
    POSITIVE LOGITS
    forums
    0.52
    dagen
    0.50
    ses
    0.49
    sor
    0.47
    s
    0.47
    的力量
    0.46
     dagen
    0.46
    oit
    0.45
    hluk
    0.44
    поль
    0.44
    Activations Density 0.003%

    No Known Activations