© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30620
    Prev
    Next
    INDEX
    Explanations

    social situations and relationships

    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
     Isk
    -1.15
     arrog
    -1.08
    iffe
    -1.02
     宣传
    -1.00
     avancer
    -0.99
     infinitesimal
    -0.99
     Cosplay
    -0.98
     mma
    -0.98
     vingt
    -0.97
     reactionary
    -0.96
    POSITIVE LOGITS
     cues
    1.28
     task
    1.15
     information
    1.15
     goal
    1.14
     presumably
    1.12
     highly
    1.11
     novel
    1.09
     distal
    1.09
     social
    1.08
     cue
    1.08
    Activations Density 0.161%

    No Known Activations