© 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. 99803
    Prev
    Next
    INDEX
    Explanations

    security hashes and company names

    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
     any
    -0.87
     despite
    -0.81
     large
    -0.81
    Other
    -0.80
    Draft
    -0.79
    Large
    -0.79
     suggest
    -0.77
     симпто
    -0.76
    lukan
    -0.76
     while
    -0.75
    POSITIVE LOGITS
     integrity
    1.41
    Integrity
    1.23
    integrity
    1.14
     integridad
    1.10
     Integrity
    1.09
    INTEGR
    0.99
     INTEGR
    0.98
    manifest
    0.97
    Bree
    0.87
    Oso
    0.85
    Activations Density 0.001%

    No Known Activations