© 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. 39751
    Prev
    Next
    INDEX
    Explanations

    involve or reduce

    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
    蓴
    -2.33
    i
    -2.31
    );
    -2.25
    ة
    -2.22
    甞
    -2.20
    鹩
    -2.17
    橦
    -2.16
    rógeno
    -2.11
    ᠂
    -2.03
     doctrina
    -2.02
    POSITIVE LOGITS
    ми
    2.59
    .”
    2.44
     econó
    2.42
     muchísimo
    2.31
     únicamente
    2.31
     básicamente
    2.28
     téc
    2.17
    ments
    2.17
     falando
    2.17
     tivesse
    2.11
    Activations Density 0.001%

    No Known Activations