© 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. 143631
    Prev
    Next
    INDEX
    Explanations

    migrants to Europe

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

    son simplycompany walkedferret impossibleThat requires

    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
    door
    0.54
    s
    0.49
    steam
    0.47
    state
    0.46
    potential
    0.46
     비슷한
    0.45
    whats
    0.44
    sets
    0.44
    potentially
    0.44
    bytes
    0.44
    POSITIVE LOGITS
    ্ু
    0.52
     Amplify
    0.52
     thoughtfulness
    0.51
    ר
    0.50
     आणि
    0.49
     aceler
    0.48
     умно
    0.48
    และ
    0.48
     cual
    0.48
    และการ
    0.48
    Activations Density 0.001%

    No Known Activations