© 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. 99962
    Prev
    Next
    INDEX
    Explanations

    programming timers

    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
    Herzlich
    -0.99
     impromptu
    -0.98
    Impressum
    -0.97
    s
    -0.94
     combing
    -0.93
    Dieser
    -0.93
     particuliers
    -0.90
    quando
    -0.88
    SEVEN
    -0.88
    Ferien
    -0.87
    POSITIVE LOGITS
     metav
    1.15
    rrrr
    1.10
    datable
    1.02
     espuma
    1.00
    rrrrrrrr
    0.98
    mint
    0.97
     palmas
    0.96
    🍷
    0.96
    atég
    0.96
    rrrrr
    0.96
    Activations Density 0.008%

    No Known Activations