© 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. 212952
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    simple crafts

    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
     comandante
    0.49
     murderer
    0.48
     CRUD
    0.46
     instru
    0.44
    यां
    0.44
     Quadrupèdes
    0.44
     στρα
    0.44
    ፕ
    0.43
     afficher
    0.43
     quân
    0.42
    POSITIVE LOGITS
    j
    0.55
    sei
    0.48
    arei
    0.48
    fifty
    0.48
    oot
    0.47
    acons
    0.47
    lated
    0.47
    hese
    0.47
    Autumn
    0.46
    erei
    0.46
    Activations Density 0.000%

    No Known Activations