© 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. 243844
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms, numbers, and objects

    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
    صبح
    0.47
    حظ
    0.47
    $),
    0.45
    cue
    0.44
     mirando
    0.44
    ")
    0.44
    }{}
    0.44
    数百
    0.43
    ]")
    0.43
    ಡೆಯ
    0.43
    POSITIVE LOGITS
     spinster
    0.52
     gown
    0.50
     paddock
    0.48
     shoreline
    0.46
     झालं
    0.46
     प्रोसेस
    0.46
     pitch
    0.46
     ferment
    0.46
     Causeway
    0.46
     sink
    0.45
    Activations Density 0.001%

    No Known Activations