© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    Then followed by various linking words

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

    soft buttons or dry

    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
    킨
    0.47
     모든
    0.46
     tämän
    0.46
     তাঁ
    0.45
     suunn
    0.45
     참여
    0.44
     بگیر
    0.44
     승
    0.43
     bushes
    0.43
     특정
    0.43
    POSITIVE LOGITS
    optimal
    0.55
    ia
    0.52
    friendly
    0.52
    heu
    0.52
    ました
    0.51
    oxidation
    0.51
    َة
    0.48
    Optimal
    0.46
    do
    0.46
    renergic
    0.46
    Activations Density 0.000%

    No Known Activations