© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168460
    Prev
    Next
    INDEX
    Explanations

    welfare systems

    np_acts-logits-general · gemini-2.5-flash-lite

    predicting potential outcomes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rec
    0.48
    ní
    0.46
    taining
    0.46
     হৃদয়
    0.46
    няет
    0.43
    }}$,
    0.43
    timestamp
    0.42
    ransition
    0.42
     kaps
    0.41
    
    0.41
    POSITIVE LOGITS
    しない
    0.53
     invers
    0.52
    AX
    0.49
     ilə
    0.47
     pamo
    0.47
    หนังสือ
    0.46
    IQ
    0.46
     chantier
    0.46
    嬋
    0.46
     lije
    0.45
    Activations Density 0.001%

    No Known Activations