© 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. 12050
    Prev
    Next
    INDEX
    Explanations

    on

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

    entity on platform

    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
     mindre
    0.39
     વખતે
    0.37
    菂
    0.37
    বার
    0.36
     Whilst
    0.36
    น้อย
    0.36
     हद
    0.35
    例文帳に追加
    0.35
     dobře
    0.35
    挎
    0.35
    POSITIVE LOGITS
     پھر
    0.40
     partnered
    0.36
     Recession
    0.35
     recession
    0.34
     partnerships
    0.34
    ऑन
    0.33
     partnering
    0.33
    anah
    0.33
     Neem
    0.33
    REPO
    0.33
    Activations Density 0.005%

    No Known Activations