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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90292
    Prev
    Next
    INDEX
    Explanations

    looks like or to

    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
     alterações
    -0.92
    issez
    -0.86
    nicy
    -0.85
    ológico
    -0.84
     résultat
    -0.84
    belum
    -0.84
    恚
    -0.84
     existing
    -0.83
     zn
    -0.83
    sibilità
    -0.83
    POSITIVE LOGITS
     destined
    1.65
     like
    1.30
     likely
    1.29
     poised
    1.27
     ready
    1.23
     primed
    1.09
     assured
    1.07
     to
    1.06
     unstoppable
    1.05
     set
    1.02
    Activations Density 0.015%

    No Known Activations