© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80881
    Prev
    Next
    INDEX
    Explanations

    U.S. patent application references

    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
     твор
    -0.79
    pole
    -0.78
     =&
    -0.77
    𝐠
    -0.76
    Bioaccumulative
    -0.76
    akuan
    -0.75
    忪
    -0.75
     dará
    -0.73
    AppMethodBeat
    -0.73
    arono
    -0.73
    POSITIVE LOGITS
    メートル
    0.75
    □
    0.73
    していて
    0.72
    чним
    0.72
     frustra
    0.71
    麩
    0.71
     magist
    0.71
     женщина
    0.69
     herum
    0.69
     ucc
    0.67
    Activations Density 0.293%

    No Known Activations