© 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. 58125
    Prev
    Next
    INDEX
    Explanations

    adjective or demonstrative followed by a noun

    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
     avowed
    -1.39
     heretofore
    -1.39
     eminently
    -1.37
     hitherto
    -1.31
     putative
    -1.30
     attendant
    -1.07
     binatang
    -1.05
    因而
    -1.05
     delights
    -1.03
     manifeste
    -1.03
    POSITIVE LOGITS
     amount
    1.07
     conocimiento
    0.98
     ideologies
    0.98
     عوامل
    0.98
     灰色
    0.97
    atguigu
    0.96
    hline
    0.96
     dessen
    0.96
     factors
    0.95
     dependiendo
    0.94
    Activations Density 0.131%

    No Known Activations