© 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. 72489
    Prev
    Next
    INDEX
    Explanations

    end of something

    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
     apresent
    -2.28
     dismin
    -2.25
     trabal
    -2.23
    ↵
    -2.16
     empez
    -2.13
     téc
    -2.11
    xvii
    -2.09
     désigne
    -2.09
     comenz
    -2.08
    ()));
    -2.05
    POSITIVE LOGITS
    1
    4.00
    7
    3.25
    6
    2.94
    2
    2.75
    是很
    2.67
    3
    2.64
    4
    2.64
    8
    2.48
    o
    2.44
    “(
    2.22
    Activations Density 0.010%

    No Known Activations