© 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. 10857
    Prev
    Next
    INDEX
    Explanations

    linking words and phrases

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

    testing and data splitting

    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
    వంటి
    0.44
    Excluded
    0.43
    Teams
    0.43
    江戸
    0.41
    anceled
    0.41
    못
    0.40
    锼
    0.40
    啊
    0.40
    ᱔
    0.40
    Нет
    0.40
    POSITIVE LOGITS
     estimates
    0.40
     práctica
    0.39
     prática
    0.39
    otest
    0.38
     przeg
    0.38
     prudence
    0.37
     살펴보
    0.37
     guards
    0.37
    estimates
    0.36
     قصد
    0.36
    Activations Density 0.000%

    No Known Activations