© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59480
    Prev
    Next
    INDEX
    Explanations

    very + intensifiers

    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
     fenomen
    -1.49
    ização
    -1.47
    圌
    -1.41
     notori
    -1.41
    
    -1.41
    を
    -1.40
    
    -1.38
     apartament
    -1.38
     sufic
    -1.37
     luni
    -1.35
    POSITIVE LOGITS
     different
    1.66
    Unlike
    1.58
     important
    1.53
     much
    1.52
     These
    1.48
    This
    1.46
     With
    1.45
     few
    1.45
     specific
    1.42
    It
    1.40
    Activations Density 0.039%

    No Known Activations