© 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. 24007
    Prev
    Next
    INDEX
    Explanations

    go to

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

    letters, stolen, A, web, available

    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
    ỏe
    0.47
    muestra
    0.45
    க்கப்பட்ட
    0.44
    یاں
    0.44
    وٹ
    0.43
    𝓌
    0.43
    offic
    0.43
    QTTR
    0.43
     каждая
    0.42
     مبنی
    0.42
    POSITIVE LOGITS
     l
    0.51
     Remo
    0.50
     Ham
    0.49
     American
    0.47
     Americans
    0.47
     angels
    0.47
     Aless
    0.47
     sc
    0.46
     Russ
    0.46
     Dres
    0.46
    Activations Density 0.000%

    No Known Activations