© 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. 85304
    Prev
    Next
    INDEX
    Explanations

    section header introductions

    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
     после
    -1.59
    После
    -1.46
     blanda
    -1.40
     beitragen
    -1.37
    ۦ
    -1.35
     pendek
    -1.34
     progressivement
    -1.31
     После
    -1.31
    neuri
    -1.30
    );}
    -1.30
    POSITIVE LOGITS
     
    2.05
     but
    1.96
     omdat
    1.48
     obvious
    1.45
     because
    1.44
    ğun
    1.43
     since
    1.42
    <sup>
    1.41
    をご紹介
    1.39
    ⢓
    1.38
    Activations Density 0.009%

    No Known Activations