© 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. 79301
    Prev
    Next
    INDEX
    Explanations

    inspired or inspection

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

    inspire

    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
     radionu
    0.57
    );}
    0.50
     preponder
    0.48
    unus
    0.47
     accentuate
    0.45
    ‌است
    0.45
     dispositivi
    0.45
    }')
    0.45
     Regents
    0.45
     impor
    0.45
    POSITIVE LOGITS
    Insider
    0.75
     Insider
    0.64
     inspections
    0.62
    5
    0.59
    Inspection
    0.58
     inspection
    0.55
     Inspection
    0.55
    4
    0.54
     insider
    0.53
    3
    0.53
    Activations Density 0.069%

    No Known Activations