© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2919
    Prev
    Next
    INDEX
    Explanations

    Dang, Dank, Dans, Dan, 登

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctional
    -0.82
    gebnisse
    -0.80
     狂
    -0.77
     admiral
    -0.75
     Feinde
    -0.74
     させ
    -0.74
    γραφ
    -0.73
    Ƣ
    -0.72
     derby
    -0.72
     szary
    -0.72
    POSITIVE LOGITS
     Kep
    0.78
    غه
    0.73
     dang
    0.73
    exper
    0.72
     Brot
    0.72
    搞笑
    0.71
    垆
    0.71
     lobe
    0.69
     boiled
    0.69
    一出
    0.68
    Activations Density 0.012%

    No Known Activations