© 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. 6845
    Prev
    Next
    INDEX
    Explanations

    Field of Invention, usage, author, summary

    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
     Bipolar
    -0.91
     ATTOR
    -0.88
    ἂ
    -0.82
    amines
    -0.81
     exquis
    -0.80
     geomet
    -0.80
     vitu
    -0.80
    心臓
    -0.80
     #####
    -0.80
     Geomet
    -0.80
    POSITIVE LOGITS
     value
    0.96
     remarks
    0.81
    alamat
    0.77
    remarks
    0.75
     MORE
    0.74
     designer
    0.73
     description
    0.73
     this
    0.71
    Remarks
    0.71
     IN
    0.71
    Activations Density 0.001%

    No Known Activations