© 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. 110564
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
     pido
    -1.01
    already
    -0.93
    according
    -0.88
    ouncement
    -0.86
     already
    -0.84
    ortal
    -0.84
    がありますが
    -0.84
     באופן
    -0.82
    Already
    -0.81
     verifique
    -0.81
    POSITIVE LOGITS
     text
    1.29
     cell
    1.29
     txt
    1.25
     TEXT
    1.18
     texting
    1.16
     or
    1.06
     texts
    1.06
    TEXT
    1.03
     phone
    1.02
     hermosa
    1.02
    Activations Density 0.017%

    No Known Activations