© 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. 51255
    Prev
    Next
    INDEX
    Explanations

    designed to, born in, quality growth

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

    legal or verification processes

    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
    FUND
    0.46
     egos
    0.45
     inscreve
    0.44
     идет
    0.44
    Terror
    0.44
     highland
    0.43
     outfield
    0.43
     э
    0.42
    Vere
    0.42
     guz
    0.42
    POSITIVE LOGITS
    ত্ত্ব
    0.52
     নির্ধার
    0.51
     Application
    0.48
    停止
    0.48
     Distance
    0.47
     Nodes
    0.47
     Tail
    0.47
    ঘ্রই
    0.46
     Rule
    0.46
     scă
    0.45
    Activations Density 0.000%

    No Known Activations