© 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. 146283
    Prev
    Next
    INDEX
    Explanations

    need for

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

    building up or condemned

    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
     sea
    0.50
     country
    0.49
     Michaelmas
    0.47
     seawater
    0.47
     ɛ
    0.47
     ochr
    0.47
     cation
    0.46
     titular
    0.46
     presenti
    0.46
     trousers
    0.46
    POSITIVE LOGITS
    簍
    0.45
    दी
    0.45
     массы
    0.45
    ABOR
    0.44
     Lifecycle
    0.44
    न्नी
    0.43
    十几
    0.43
    রত্ব
    0.43
    IRT
    0.42
    顱
    0.42
    Activations Density 0.001%

    No Known Activations