© 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. 27038
    Prev
    Next
    INDEX
    Explanations

    disability lawyer

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

    changes and industries

    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
     opcao
    0.48
    '});
    0.47
    "});
    0.45
     Königs
    0.44
    '^
    0.43
     ausgest
    0.42
     matemáticas
    0.42
    '><
    0.41
     Array
    0.41
    '}).
    0.41
    POSITIVE LOGITS
    cies
    0.53
     strengths
    0.49
    ंबर्स
    0.49
    econom
    0.48
     markedly
    0.46
     ब्रि
    0.45
    शीट
    0.45
     वाटर
    0.44
    シティ
    0.44
    ರುಗ
    0.43
    Activations Density 0.000%

    No Known Activations