© 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. 19051
    Prev
    Next
    INDEX
    Explanations

    phone numbers and codes

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

    data and labels

    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
     EditText
    0.49
     ayudarte
    0.45
     você
    0.45
     guerras
    0.45
     wallpapers
    0.44
     chatbots
    0.44
     деву
    0.44
     給
    0.43
     apartheid
    0.43
     mysql
    0.42
    POSITIVE LOGITS
    Prime
    0.46
    NZ
    0.45
    Designed
    0.45
    Optional
    0.44
    Agents
    0.44
    厂
    0.44
    Doctors
    0.43
    Traditionally
    0.43
    Historically
    0.43
    Three
    0.42
    Activations Density 0.000%

    No Known Activations