© 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. 31018
    Prev
    Next
    INDEX
    Explanations

    following `to` or `their`

    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
     kem
    -1.02
     lavable
    -0.90
     וה
    -0.89
     مباراة
    -0.88
     Entre
    -0.87
    としては
    -0.87
     casi
    -0.85
     sosis
    -0.85
    鰹
    -0.85
    منبع
    -0.84
    POSITIVE LOGITS
    izzati
    1.05
     عليهم
    1.00
     hangover
    0.98
    Drainage
    0.93
     sermon
    0.90
    naies
    0.89
    жах
    0.86
     glycerin
    0.86
    okok
    0.86
    especie
    0.86
    Activations Density 0.052%

    No Known Activations