© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108147
    Prev
    Next
    INDEX
    Explanations

    sweet spot

    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
    ベーション
    -0.78
    ╵
    -0.77
    মান
    -0.77
    Sala
    -0.75
     Traces
    -0.74
     enri
    -0.74
    KURZBESCHREIBUNG
    -0.74
    輩
    -0.73
    waż
    -0.73
     백
    -0.73
    POSITIVE LOGITS
     sweet
    5.06
    sweet
    4.31
     Sweet
    3.91
    Sweet
    3.67
    SWEET
    3.03
     SWEET
    3.02
     слад
    2.73
     sweetest
    2.31
     sweetness
    2.17
     sweetly
    2.09
    Activations Density 0.042%

    No Known Activations