© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1873
    Prev
    Next
    INDEX
    Explanations

    network services and admin

    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
    ود
    -0.73
     Schülern
    -0.70
     především
    -0.69
     कर
    -0.69
    presso
    -0.68
    輩
    -0.68
    ceph
    -0.66
    לח
    -0.66
     cứng
    -0.65
     Ebenen
    -0.65
    POSITIVE LOGITS
     tel
    1.12
     Accounting
    0.93
     Console
    0.93
     Finger
    0.91
     console
    0.88
     Tel
    0.86
     NIS
    0.84
     dial
    0.84
     accounting
    0.83
    accounting
    0.83
    Activations Density 0.084%

    No Known Activations