© 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. 93182
    Prev
    Next
    INDEX
    Explanations

    if or why questions

    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
     also
    -1.17
     hoeveel
    -1.09
    lawesi
    -1.09
     فبراير
    -1.08
     beroep
    -1.06
     need
    -1.05
     segíts
    -1.05
    alakip
    -1.05
    
    -1.04
     repeal
    -1.03
    POSITIVE LOGITS
     by
    2.02
     it
    1.53
     orchestr
    1.43
     taking
    1.42
     doing
    1.20
     getting
    1.20
     dedic
    1.17
     tuyau
    1.17
     putting
    1.16
     giving
    1.14
    Activations Density 0.107%

    No Known Activations