© 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. 90338
    Prev
    Next
    INDEX
    Explanations

    names like Ryan, Scott, Reed, or words like Group, Jet

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

    distinct values

    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
    ui
    0.53
    on
    0.48
    án
    0.47
    αι
    0.46
    ìm
    0.45
    ὧ
    0.45
    ライド
    0.45
    rá
    0.44
    ía
    0.44
    rio
    0.44
    POSITIVE LOGITS
     Business
    0.43
    蔑
    0.42
     "*************"
    0.42
     실
    0.42
     İn
    0.41
     LinkedIn
    0.41
     insofar
    0.40
     топо
    0.40
     Tiger
    0.39
     컴퓨
    0.39
    Activations Density 0.001%

    No Known Activations