© 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. 235045
    Prev
    Next
    INDEX
    Explanations

    economis growth

    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
    ﺏ
    0.50
     த
    0.49
    ச்
    0.47
     lâu
    0.46
    נדה
    0.46
    ্স
    0.46
    בור
    0.45
     புதிய
    0.45
     அருகில்
    0.45
    Xpaths
    0.44
    POSITIVE LOGITS
     Vols
    0.47
     pertence
    0.46
     inds
    0.46
    voll
    0.46
     Chiche
    0.45
     Vol
    0.45
    u
    0.45
     editorial
    0.45
     recommending
    0.44
     Ấ
    0.44
    Activations Density 0.001%

    No Known Activations