© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47211
    Prev
    Next
    INDEX
    Explanations

    end of sentence or section

    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
    Negative Logits
    ")
    -0.79
    "]
    -0.76
    　・
    -0.75
    "")
    -0.72
    ⌝
    -0.71
    shard
    -0.70
     subsection
    -0.70
    `)
    -0.70
    ）
    -0.70
    kans
    -0.69
    POSITIVE LOGITS
     end
    1.91
    end
    1.54
    END
    1.22
     End
    1.18
    エンド
    1.13
    End
    1.11
    ></
    1.11
     }}"></
    1.08
    ."</
    1.07
     ends
    1.05
    Activations Density 0.016%

    No Known Activations