© 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. 30979
    Prev
    Next
    INDEX
    Explanations

    people involved in events

    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
    1
    -1.10
    3
    -1.10
    m
    -1.05
    ]
    -1.03
    7
    -1.02
    4
    -0.99
    f
    -0.94
    

    -0.94
    9
    -0.93
     result
    -0.93
    POSITIVE LOGITS
     who
    2.83
     whom
    1.55
    whom
    1.50
     whose
    1.48
    hips
    1.46
     extraordinaire
    1.32
     from
    1.25
    뿅
    1.22
    Who
    1.20
     siapa
    1.20
    Activations Density 0.088%

    No Known Activations