© 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. 32525
    Prev
    Next
    INDEX
    Explanations

    Q / Now / import follows by text

    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
     Abgerufen
    -0.77
    。)
    -0.75
     gradually
    -0.74
    旭
    -0.73
     inga
    -0.70
     изменить
    -0.70
    สั่ง
    -0.70
     Bauch
    -0.69
     took
    -0.68
    spedes
    -0.67
    POSITIVE LOGITS
    muchas
    0.89
     acceptance
    0.85
     Acceptance
    0.85
    sers
    0.81
     accepting
    0.81
    espacio
    0.80
    isesi
    0.79
    acceptance
    0.79
     Cushing
    0.79
    accept
    0.78
    Activations Density 0.004%

    No Known Activations