© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246847
    Prev
    Next
    INDEX
    Explanations

    legal and parenting contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nigris
    0.46
     Gauge
    0.46
     Bois
    0.44
     reinforcement
    0.43
     Handling
    0.43
     ytter
    0.43
     Estimation
    0.43
     reinforcing
    0.42
    细
    0.42
    异
    0.42
    POSITIVE LOGITS
    javab
    0.55
    gli
    0.50
    mel
    0.50
    interpreter
    0.50
    icato
    0.49
    ila
    0.49
    inho
    0.49
    pp
    0.49
    him
    0.49
    ponsor
    0.48
    Activations Density 0.001%

    No Known Activations