© 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. 111280
    Prev
    Next
    INDEX
    Explanations

    stay together

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

    contextual phrases

    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
    ar
    0.54
    первых
    0.50
     первый
    0.50
     прошла
    0.49
    ।
    0.48
    Universe
    0.48
    。
    0.48
    하면
    0.48
    playerId
    0.47
     черный
    0.47
    POSITIVE LOGITS
     সক্ষম
    0.44
     proxim
    0.44
     überw
    0.44
     presso
    0.43
     Sudan
    0.43
     Equivalent
    0.42
     assimil
    0.42
     Termination
    0.42
     immun
    0.41
     Edmonton
    0.41
    Activations Density 0.001%

    No Known Activations