© 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. 37113
    Prev
    Next
    INDEX
    Explanations

    human condition

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

    water promotes corrosion

    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
     oček
    0.49
     dox
    0.47
     crois
    0.47
     frutos
    0.45
     buka
    0.45
     falei
    0.45
    ▇
    0.45
     estrella
    0.45
     však
    0.44
     fabricant
    0.44
    POSITIVE LOGITS
    Bibliography
    0.51
     Text
    0.45
     Database
    0.45
    `).
    0.44
    setRequestHeader
    0.44
     Function
    0.43
     Dictionary
    0.43
     Irrigation
    0.43
    💾
    0.43
     Bibliography
    0.42
    Activations Density 0.000%

    No Known Activations