© 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. 135844
    Prev
    Next
    INDEX
    Explanations

    "Monsters", Romney, new, odors

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

    defined terms for algorithms and concepts

    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
    IRE
    0.52
    erd
    0.51
    EE
    0.51
    Engine
    0.51
     étude
    0.48
    يديو
    0.47
    ére
    0.47
    *
    0.47
    ED
    0.46
    數據
    0.46
    POSITIVE LOGITS
     nė
    0.47
     उपलब्ध
    0.46
     čovjek
    0.45
     नतीजे
    0.45
     সী
    0.44
     golongan
    0.44
     tribune
    0.44
    thebetterindia
    0.44
     refrigerant
    0.43
     faci
    0.42
    Activations Density 0.000%

    No Known Activations