© 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. 78031
    Prev
    Next
    INDEX
    Explanations

    Field of the invention

    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
     PÅ
    -1.17
     GARANT
    -1.13
     éte
    -1.09
     exé
    -1.05
     SITY
    -1.04
     régle
    -1.04
     rembourse
    -1.02
     répon
    -1.02
     UNIVE
    -1.00
     operacional
    -1.00
    POSITIVE LOGITS
     was
    1.05
    ……
    1.02
     BY
    1.00
     is
    1.00
     miesz
    0.98
     isn
    0.97
     …
    0.96
     what
    0.94
    。
    0.93
    から
    0.93
    Activations Density 0.013%

    No Known Activations