© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    code keywords followed by colons

    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
     zosta
    -1.06
    之前
    -1.04
     Scritto
    -1.02
    necessary
    -1.01
     viewWillAppear
    -1.00
    仍然
    -0.99
    logrus
    -0.98
    依然
    -0.98
    föl
    -0.98
    ditional
    -0.97
    POSITIVE LOGITS
     because
    0.90
     Olympedia
    0.88
    児童
    0.87
     what
    0.84
     According
    0.83
     handover
    0.81
     Roumanie
    0.80
     促销
    0.79
     contributory
    0.79
    érance
    0.76
    Activations Density 0.055%

    No Known Activations