© 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. 117331
    Prev
    Next
    INDEX
    Explanations

    personal information, mom, federal, eternal

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

    context and categories

    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
     Mes
    0.53
     Sele
    0.50
     May
    0.49
     Decl
    0.49
    ’
    0.49
     recibir
    0.48
     Feb
    0.45
     Meeting
    0.45
     América
    0.45
     Neces
    0.45
    POSITIVE LOGITS
    openide
    0.50
     этими
    0.48
    netHex
    0.46
    ဓ
    0.46
    oresis
    0.44
     λόγω
    0.44
    нього
    0.43
    textfield
    0.42
    adari
    0.42
     pastoral
    0.41
    Activations Density 0.000%

    No Known Activations