© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109694
    Prev
    Next
    INDEX
    Explanations

    not so [descriptor]

    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
     varier
    -1.35
     accél
    -1.25
     assez
    -1.23
     konfigura
    -1.23
     systé
    -1.20
    鶿
    -1.20
    relatively
    -1.20
     praticamente
    -1.20
     スケッチ
    -1.15
    albeit
    -1.14
    POSITIVE LOGITS
     easy
    1.36
     great
    1.25
     much
    1.14
     new
    1.13
     old
    1.11
    After
    1.08
     k
    1.06
       
    1.05
     hot
    1.05
     good
    1.04
    Activations Density 0.007%

    No Known Activations