© 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. 22-GEMMASCOPE-RES-131K
    7. 16213
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    REQ
    -1.17
     recenz
    -1.13
    Û
    -1.09
     gwaran
    -1.07
     blusa
    -1.05
    резать
    -1.05
     décid
    -1.03
    のもの
    -1.02
     Cette
    -1.02
     évident
    -1.01
    POSITIVE LOGITS
     is
    1.08
     and
    1.05
     impostor
    0.95
    สามารถ
    0.94
     XG
    0.94
     NTIS
    0.93
    瑣
    0.93
    において
    0.93
     can
    0.91
     abomination
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.