© 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. 20275
    Prev
    Next
    INDEX
    Explanations

    numbers and phone numbers

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

    explaining the outcome of a process

    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
    PARTY
    0.55
    ПР
    0.54
    ОР
    0.54
    UNITY
    0.52
    ㄥ
    0.52
    ДО
    0.51
    З
    0.50
    𝑃
    0.50
    TUR
    0.50
    ウン
    0.49
    POSITIVE LOGITS
     UI
    0.49
     Seo
    0.45
     Wallace
    0.43
     SI
    0.43
     finalised
    0.43
     intros
    0.43
     l
    0.42
     mainstream
    0.42
     Full
    0.41
     Appl
    0.41
    Activations Density 0.000%

    No Known Activations