© 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. 10-GEMMASCOPE-RES-131K
    7. 44266
    Prev
    Next
    INDEX
    Explanations

    prior art and related art

    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_10/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
     their
    -2.34
     because
    -1.88
     cualquier
    -1.49
     orice
    -1.45
    olge
    -1.44
    >');
    -1.43
    DebuggerNonUser
    -1.40
     atau
    -1.38
    ledad
    -1.38
    ofing
    -1.37
    POSITIVE LOGITS
     to
    1.95
     into
    1.91
    jenigen
    1.55
    :
    1.44
    complished
    1.41
     jedynie
    1.36
    下さ
    1.29
    になっている
    1.29
     增加
    1.29
     incrementar
    1.28
    Activations Density 0.139%

    No Known Activations