© 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. 151302
    Prev
    Next
    INDEX
    Explanations

    institutional operations and security

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

    Lack of motivation

    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
     viu
    0.49
    변
    0.45
    цију
    0.44
    пробу
    0.44
    水位
    0.44
    慚
    0.44
     vio
    0.43
    න්ත
    0.43
     beginnen
    0.42
     solitaire
    0.42
    POSITIVE LOGITS
    二
    0.46
     Hungarian
    0.44
     insufficiently
    0.44
     Russian
    0.42
     FIGURES
    0.42
     CHINA
    0.41
    hobby
    0.41
     Gruber
    0.40
     reportedly
    0.39
    缺乏
    0.39
    Activations Density 0.003%

    No Known Activations