© 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. 23300
    Prev
    Next
    INDEX
    Explanations

    adjective or noun following article

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

    social interactions and advice

    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
    ﭜ
    0.52
    十七
    0.48
    ناوی
    0.46
    щаются
    0.46
     اڈوں
    0.45
    Yep
    0.45
    ત્રી
    0.44
     Orient
    0.43
     ¹
    0.43
    ρα
    0.43
    POSITIVE LOGITS
     judiciales
    0.52
    ictionaries
    0.51
     त्र
    0.51
     কল
    0.50
     চিৎ
    0.49
     overlays
    0.48
    िक्ट
    0.48
     sentimiento
    0.48
     polite
    0.47
     lids
    0.47
    Activations Density 0.000%

    No Known Activations