© 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. 130817
    Prev
    Next
    INDEX
    Explanations

    covering needs and solutions

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

    fact, run, overall, directly, education, poor health, jailbreaking

    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
    panelMenuList
    0.43
    wang
    0.43
     pavatt
    0.43
     왕
    0.43
    pele
    0.43
    capt
    0.43
     پھر
    0.42
     इन्हें
    0.42
     बेरोज
    0.41
     preparado
    0.40
    POSITIVE LOGITS
    )
    0.54
    )?
    0.49
    
    0.47
     Mund
    0.44
     STREET
    0.44
    এম
    0.44
     Avid
    0.44
    Һ
    0.44
     linebreak
    0.43
    ùng
    0.43
    Activations Density 0.001%

    No Known Activations