© 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. 165796
    Prev
    Next
    INDEX
    Explanations

    professionals that, feed two, place and

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

    endorse and invalidate

    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
    jun
    0.46
    Когда
    0.46
    І
    0.46
     vanwege
    0.45
    swith
    0.45
    Heb
    0.45
    iraj
    0.44
     consecutively
    0.44
    铿
    0.43
    因為
    0.43
    POSITIVE LOGITS
     হয়েছিল
    0.46
     investors
    0.45
    新たな
    0.43
     inefficiency
    0.42
     membayar
    0.42
     implica
    0.42
     huyện
    0.42
     sabía
    0.42
     inefficiencies
    0.42
     influent
    0.42
    Activations Density 0.001%

    No Known Activations