© 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. 4755
    Prev
    Next
    INDEX
    Explanations

    often, various, very

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

    one entity to another

    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
    虚
    0.40
     Cabo
    0.35
    Action
    0.35
    Actual
    0.35
    Show
    0.35
    Canon
    0.34
    略
    0.34
    颁
    0.34
    园
    0.34
     Rizzo
    0.34
    POSITIVE LOGITS
     spesso
    0.51
     mudah
    0.49
    鵃
    0.47
     vaak
    0.44
     பல்வேறு
    0.44
     વિવિધ
    0.44
     milioane
    0.44
     ज्यादातर
    0.43
     ofta
    0.43
     বড়ই
    0.41
    Activations Density 0.030%

    No Known Activations