© 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. 51376
    Prev
    Next
    INDEX
    Explanations

    but, possibly, especially

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

    especially this part

    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
    ilis
    0.45
     তিনিও
    0.38
    /).
    0.36
    ŭ
    0.36
     összes
    0.35
     державних
    0.35
     遅
    0.35
    徐
    0.35
     Algunas
    0.34
    จุบัน
    0.34
    POSITIVE LOGITS
     vooral
    1.20
    最重要的
    1.20
     surtout
    1.16
     przede
    1.16
     principalmente
    1.15
     soprattutto
    1.15
     terutama
    1.06
     সবচেয়ে
    1.05
     najważ
    1.05
     především
    1.05
    Activations Density 0.088%

    No Known Activations