© 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. 84835
    Prev
    Next
    INDEX
    Explanations

    successful outcome

    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
     The
    -3.97
     OTHER
    -3.17
     '
    -3.16
     เมื่อ
    -3.03
     unbelievably
    -3.02
     当
    -2.97
     decidedly
    -2.95
     ridiculously
    -2.94
     pivotal
    -2.91
     bleak
    -2.77
    POSITIVE LOGITS
    …”
    3.67
    :”
    3.47
    酲
    3.34
    стреча
    3.28
    ,’
    3.25
    玙
    3.22
    𓆜
    3.14
    новь
    3.08
    —“
    3.06
    нутрен
    3.02
    Activations Density 0.011%

    No Known Activations