© 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. 73838
    Prev
    Next
    INDEX
    Explanations

    disruptive marketplaces, insert, folklore, infused

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

    investigates stolen

    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
    ionu
    0.51
    ਨੀ
    0.48
    囫
    0.47
    ionine
    0.47
    hiyam
    0.46
     condições
    0.45
     हॉट
    0.45
     विवेक
    0.44
     度
    0.44
     विज्ञापन
    0.44
    POSITIVE LOGITS
    D
    0.53
    DL
    0.43
     TECH
    0.42
    еди
    0.41
    E
    0.40
    電
    0.40
     militar
    0.39
    電動
    0.39
    Fiat
    0.39
    зва
    0.39
    Activations Density 0.000%

    No Known Activations