© 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. 99895
    Prev
    Next
    INDEX
    Explanations

    do something or something else

    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
    ļ
    -0.84
    мый
    -0.84
    Ľ
    -0.81
    illa
    -0.80
    ーパー
    -0.79
    problem
    -0.79
    εια
    -0.78
    ZE
    -0.78
    iba
    -0.77
    zuk
    -0.76
    POSITIVE LOGITS
     amazing
    2.22
     interesting
    2.22
     wonderful
    2.20
     great
    1.91
     terrible
    1.72
     things
    1.68
     strange
    1.68
     exciting
    1.66
     bad
    1.63
     remarkable
    1.60
    Activations Density 0.070%

    No Known Activations