© 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. 184210
    Prev
    Next
    INDEX
    Explanations

    airline, gaming, mission, computer

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

    specific terms followed by definitions

    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
    できた
    0.47
    孫
    0.46
    ◯
    0.46
    搭配
    0.45
    ﾆ
    0.45
     fácil
    0.45
    ブ
    0.45
    思う
    0.44
    тила
    0.43
    コ
    0.43
    POSITIVE LOGITS
    etrics
    0.49
    hnt
    0.48
     Indies
    0.47
    ઁ
    0.47
    agh
    0.47
    hota
    0.47
    porte
    0.46
     Ork
    0.46
    urr
    0.46
    hore
    0.46
    Activations Density 0.000%

    No Known Activations