© 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. 127747
    Prev
    Next
    INDEX
    Explanations

    closing on property, bankruptcy proceedings, starting something

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

    liminality and transition

    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
     Bird
    0.54
     Mounting
    0.53
     Flower
    0.50
    }}
    0.50
    wil
    0.50
     t
    0.49
     Nov
    0.48
     This
    0.48
     Wil
    0.48
     Item
    0.47
    POSITIVE LOGITS
     घेतले
    0.53
     忄
    0.51
     undeni
    0.50
     thermodynam
    0.50
     proactively
    0.50
    ेलर
    0.49
     portray
    0.48
    รง
    0.48
     आरमार
    0.48
     طلبه
    0.47
    Activations Density 0.000%

    No Known Activations